We study leveraging adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval.Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial query.While existing reasoning-based reranker pipelines attempt to surface these documents in ranking, they suffer from bounded recall.Naive solution with adaptive retrieval into these pipelines often leads to planning error propagation.To address this, we propose REPAIR, a framework that bridges this gap by repurposing reasoning plans as dense feedback signals for adaptive retrieval.Our key distinction is enabling mid-course correction during reranking through selective adaptive retrieval, retrieving documents that support the pivotal plan.Experimental results on reasoning-intensive retrieval and complex QA tasks demonstrate that our method outperforms existing baselines by 5.6%pt.

Large reasoning models (LRMs) achieve strong performance by externalizing explicit reasoning traces before producing the answer, yet suffer from overthinking challenge that allocates uniformly heavy computation to queries of varying difficulty.While proprietary models mitigate this via opaque routing, open-source LRMs still lack an efficient mechanism to internalize adaptive reasoning due to both expensive training cost and limited disclosure of training recipes.In response, we introduce RPO (Roottoken Policy Optimization), a framework that enables LRMs to self-determine when to reason by training only the initial root token (e.g., whether to invoke the tag) via group relative reward and group-wise advantages.By focusing on this pivotal branching point, RPO drastically reduces training overhead and VRAM usage.Across multiple model families and scales, RPO learns difficulty-aware adaptive thinking at just ∼2% of the training compute of prior adaptive-reasoning methods.

Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels. While there exist various 2D graph-based molecular pretraining approaches, these methods struggle to show statistically significant gains in predictive performance. Recent work have thus instead proposed 3D conformer-based pretraining under the task of denoising, leading to promising results. During downstream finetuning, however, models trained with 3D conformers require accurate atom-coordinates of previously unseen molecules, which are computationally expensive to acquire at scale. In this paper, we propose a simple solution of denoise-and-distill (D&D), a self-supervised molecular representation learning method that pretrains a 2D graph encoder by distilling representations from a 3D denoiser. With denoising followed by cross-modal knowledge distillation, our approach enjoys use of knowledge obtained from denoising as well as painless application to downstream tasks with no access to 3D conformers. Experiments on real-world molecular property prediction datasets show that the graph encoder trained via D&D can infer 3D information based on the 2D graph and shows superior performance and label-efficiency against previous methods.

Retrieval in Retrieval-Augmented Generation (RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set.Existing approaches primarily rerank top-k passages based on their individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering.In this work, we propose a set-wise passage selection approach and introduce SETR, which explicitly identifies the information requirements of a query through Chain-of-Thought reasoning and selects an optimal set of passages that collectively satisfy those requirements.Experiments on multi-hop RAG benchmarks show that SETR outperforms both proprietary LLM-based rerankers and open-source baselines in terms of answer correctness and retrieval quality, providing an effective and efficient alternative to traditional rerankers in RAG systems.

The value orientation of Large Language Models (LLMs) has been extensively studied, as it can shape user experiences across demographic groups.However, two key challenges remain:(1) the lack of systematic comparison across value probing strategies, despite the Multiple Choice Question (MCQ) setting being vulnerable to perturbations, and (2) the uncertainty over whether probed values capture in-context information or predict models' real-world actions.In this paper, we systematically compare three widely used value probing methods: token likelihood, sequence perplexity, and text generation.Our results show that all three methods exhibit large variances under non-semantic perturbations in prompts and option formats, with sequence perplexity being the most robust overall.We further introduce two tasks to assess expressiveness: demographic prompting, testing whether probed values adapt to cultural context; and value-action agreement, testing the alignment of probed values with value-based actions.We find that demographic context has little effect on the text generation method, and probed values only weakly correlate with action preferences across all methods.Our work highlights the instability and the limited expressive power of current value probing methods, calling for more reliable LLM value representations.

Hyungyu Shin, Jingyu Tang, Yoonjoo Lee, Nayoung Kim, Hyunseung Lim, Ji Yong Cho, Hwajung Hong, Moontae Lee, Juho Kim. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods that remove sensitive data without retraining from scratch. While Gradient Ascent (GA) is commonly used to unlearn by reducing the likelihood of generating unwanted content, it leads to unstable optimization and catastrophic forgetting of retrained knowledge. We find that combining GA with low-rank adaptation results in poor trade-offs between computational cost and generative performance. To address these challenges, we propose Low-rank Knowledge Unlearning (LoKU), a novel framework that enables robust and efficient unlearning for LLMs. First, we introduce Inverted Hinge Loss, which suppresses unwanted tokens while maintaining fluency by boosting the probability of the next most likely token. Second, we develop a data-adaptive initialization for LoRA adapters via low-rank approximation weighted with relative Fisher information, thereby focusing updates on parameters critical for removing targeted knowledge. Experiments on the Training Data Extraction Challenge dataset using GPT-Neo models as well as on the TOFU benchmark with Phi-1.5B and Llama2-7B models demonstrate that our approach effectively removes sensitive information while maintaining reasoning and generative capabilities with minimal impact. Our implementation can be found in https://github.com/csm9493/efficient-llm-unlearning.

Efficient access to high-quality information is vital for online platforms. To promote more useful information, users not only create new content but also evaluate existing content, often through helpfulness voting. Although aggregated votes help service providers rank their user content, these votes are often biased by disparate accessibility per position and the cascaded influence of prior votes. For a fairer assessment of information quality, we propose the Counterfactual Voting Adjustment (CVA), a causal framework that accounts for the context in which individual votes are cast. Through preliminary and semi-synthetic experiments, we show that CVA effectively models the position and herding biases, accurately recovering the predefined content quality. In a real experiment, we demonstrate that reranking content based on the learned quality by CVA exhibits stronger alignment with both user sentiment and quality evaluation assessed by GPT-4o, outperforming system rankings based on aggregated votes and model-based rerankings without causal inference. Beyond the individual quality inference, our embeddings offer comparative insights into the behavioral dynamics of expert user groups across 120 major StackExchange communities.

Seungone Kim, Juyoung Suk, Ji Yong Cho, Shayne Longpre, Chaeeun Kim, Dongkeun Yoon, Guijin Son, Yejin Cho, Sheikh Shafayat, Jinheon Baek, Sue Hyun Park, Hyeonbin Hwang, Jinkyung Jo, Hyowon Cho, Haebin Shin, Seongyun Lee, Hanseok Oh, Noah Lee, Namgyu Ho, Se June Joo, Miyoung Ko, Yoonjoo Lee, Hyungjoo Chae, Jamin Shin, Joel Jang, Seonghyeon Ye, Bill Yuchen Lin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, Minjoon Seo. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

AI-generated image detection has become crucial with the rapid advancement of vision-generative models. Instead of training detectors tailored to specific datasets, we study a training-free approach leveraging self-supervised models without requiring prior data knowledge. These models, pre-trained with augmentations like $\texttt{RandomResizedCrop}$, learn to produce consistent representations across varying resolutions. Motivated by this, we propose $\textbf{WaRPAD},$ a training-free AI-generated image detection algorithm based on self-supervised models. Since neighborhood pixel differences in images are highly sensitive to resizing operations, WaRPAD first defines a base score function that quantifies the sensitivity of image embeddings to perturbations along high-frequency directions extracted via Haar wavelet decomposition. To simulate robustness against cropping augmentation, we rescale each image to a multiple of the model’s input size, divide it into smaller patches, and compute the base score for each patch. The final detection score is then obtained by averaging the scores across all patches. We validate WaRPAD on real datasets of diverse resolutions and domains, and images generated by 23 different generative models. Our method consistently achieves competitive performance and demonstrates strong robustness to test-time corruptions. Furthermore, as invariance to $\texttt{RandomResizedCrop}$ is a common training scheme across self-supervised models, we show that WaRPAD is applicable across self-supervised models.

Patent examination remains an ongoing challenge in the NLP literature even after the advent of large language models (LLMs), as it requires an extensive yet nuanced human judgment on whether a submitted $\textit{claim}$ meets the statutory standards of $\textit{novelty}$ and $\textit{non-obviousness}$ against previously granted claims—$\textit{prior art}$—in expert domains. Previous NLP studies have approached this challenge as a prediction task (e.g., forecasting grant outcomes) with high-level proxies such as similarity metrics or classifiers trained on historical labels. However, this approach often overlooks the step-by-step evaluations that examiners must make with profound information, including rationales for the decisions provided in $\textit{office actions}$ documents, which also makes it harder to measure the current state of techniques in patent review processes. To fill this gap, we construct PANORAMA, a dataset of 8,143 U.S. patent examination records that preserves the full decision trails, including original applications, all cited references, $\textit{Non-Final Rejections}$, and $\textit{Notices of Allowance}$. Also, PANORAMA decomposes the trails into sequential benchmarks that emulate patent professionals' patent review processes and allow researchers to examine large language models' capabilities at each step of them. Our findings indicate that, although LLMs are relatively effective at retrieving relevant prior art and pinpointing the pertinent paragraphs, they struggle to assess the novelty and non-obviousness of patent claims. We discuss these results and argue that advancing NLP, including LLMs, in the patent domain requires a deeper understanding of real-world patent examination. Our dataset is openly available at https://huggingface.co/datasets/LG-AI-Research/PANORAMA.

We introduce MLRC-Bench, a benchmark designed to quantify how effectively language agents can tackle challenging Machine Learning (ML) Research Competitions, with a focus on open research problems that demand novel methodologies.Unlike prior work, e.g., AI Scientist, which evaluates the end-to-end agentic pipeline by using LLM-as-a-judge, MLRC-Bench measures the key steps of proposing and implementing novel research methods and evaluates them with rigorous protocol and objective metrics.Our curated suite of 7 competition tasks reveals significant challenges for LLM agents. Even the best-performing tested agent (gemini-exp-1206 under MLAB) closes only 9.3% of the gap between baseline and top human participant scores.Furthermore, our analysis reveals a misalignment between the LLM-judged innovation and their actual performance on cutting-edge ML research problems. MLRC-Bench is a dynamic benchmark, which is designed to continually grow with new ML competitions to encourage rigorous and objective evaluations of AI’s research capabilities. Our leaderboard and code are publicly available at https://huggingface.co/spaces/launch/MLRC_Bench.

Research promotion enables researchers to share advanced knowledge with pertinent academic communities. The question-and-answer (QA) style articles are effective for researchers to promote their research by enabling readers to understand research on complex subjects. Recent advances in large language models (LLMs) have opened avenues for supporting researchers in creating QA-style articles for research promotion. However, without the authors’ involvement, these models may only partially capture the researcher’s intention and voice. We developed AQUA, a research probe that enables researchers to co-create QA-style articles with LLMs to promote their research papers. A user study (n=12) reveals that LLMs reduced authors’ burden and helped them understand the readers’ perspectives. Nevertheless, LLMs failed to capture the unique intent of the authors, and their automated generation discouraged authors from carefully revising their answers. Based on our findings, we discuss human-LLM interaction design to enable authors to create QA-style articles that reflect their intention.

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from scratch. The inherent vulnerability of neural networks towards adversarial attacks and unfairness also calls for a robust method to remove or correct information in an instance-wise fashion, while retaining the predictive performance across remaining data. To this end, we consider instance-wise unlearning, of which the goal is to delete information on a set of instances from a pre-trained model, by either misclassifying each instance away from its original prediction or relabeling the instance to a different label. We also propose two methods that reduce forgetting on the remaining data: 1) utilizing adversarial examples to overcome forgetting at the representation-level and 2) leveraging weight importance metrics to pinpoint network parameters guilty of propagating unwanted information. Both methods only require the pre-trained model and data instances to forget, allowing painless application to real-life settings where the entire training set is unavailable. Through extensive experimentation on various image classification benchmarks, we show that our approach effectively preserves knowledge of remaining data while unlearning given instances in both single-task and continual unlearning scenarios.

Instructional videos provide detailed how-to guides for various tasks, with viewers often posing questions regarding the content. Addressing these questions is vital for comprehending the content, yet receiving immediate answers is difficult. While numerous computational models have been developed for Video Question Answering (Video QA) tasks, they are primarily trained on questions generated based on video content, aiming to produce answers from within the content. However, in real-world situations, users may pose questions that go beyond the video's informational boundaries, highlighting the necessity to determine if a video can provide the answer. Discerning whether a question can be answered by video content is challenging due to the multi-modal nature of videos, where visual and verbal information are intertwined. To bridge this gap, we present the YTCommentQA dataset, which contains naturally-generated questions from YouTube, categorized by their answerability and required modality to answer -- visual, script, or both. Experiments with answerability classification tasks demonstrate the complexity of YTCommentQA and emphasize the need to comprehend the combined role of visual and script information in video reasoning. The dataset is available at https://github.com/lgresearch/YTCommentQA.

Seungone Kim, Juyoung Suk, Shayne Longpre, Bill Yuchen Lin, Jamin Shin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, Minjoon Seo. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

As the pre-training objectives (e.g., next token prediction) of language models (LMs) are inherently not aligned with task scores, optimizing LMs to achieve higher downstream task scores is essential. One of the promising approaches is to fine-tune LMs through reinforcement learning (RL). However, conventional RL methods based on PPO and a penalty of KL divergence are vulnerable to text degeneration where LMs do not generate natural texts anymore after RL fine-tuning. To address this problem, we provide Degeneration-free Policy Optimization (DfPO) that can fine-tune LMs to generate texts that achieve improved downstream task scores, while preserving the ability to generate natural texts. To achieve this, we introduce KL-masking which masks out the actions that potentially cause deviation from the reference policy when its likelihood is increased or decreased. Then, we devise truncated advantage functions for separately performing likelihood maximization and minimization to improve the task performance. In the experiments, we provide the results of DfPO and baseline algorithms on various generative NLP tasks including text continuation, text detoxification, and commonsense generation. Our experiments demonstrate that DfPO successfully improves the downstream task scores while preserving the ability to generate natural texts, without requiring additional hyperparameter search.

Lajanugen Logeswaran, Sungryull Sohn, Yiwei Lyu, Anthony Liu, Dong-Ki Kim, Dongsub Shim, Moontae Lee, Honglak Lee. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Siqi Shen, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Soujanya Poria, Rada Mihalcea. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Bangzhao Shu, Lechen Zhang, Minje Choi, Lavinia Dunagan, Lajanugen Logeswaran, Moontae Lee, Dallas Card, David Jurgens. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Graph pooling is a crucial operation for encoding hierarchical structures within graphs. Most existing graph pooling approaches formulate the problem as a node clustering task which effectively captures the graph topology. Conventional methods ask users to specify an appropriate number of clusters as a hyperparameter, then assuming that all input graphs share the same number of clusters. In inductive settings where the number of clusters could vary, however, the model should be able to represent this variation in its pooling layers in order to learn suitable clusters. Thus we propose GMPool, a novel differentiable graph pooling architecture that automatically determines the appropriate number of clusters based on the input data. The main intuition involves a grouping matrix defined as a quadratic form of the pooling operator, which induces use of binary classification probabilities of pairwise combinations of nodes. GMPool obtains the pooling operator by first computing the grouping matrix, then decomposing it. Extensive evaluations on molecular property prediction tasks demonstrate that our method outperforms conventional methods.

Joel Jang, Dongkeun Yoon, Sohee Yang, Sungmin Cha, Moontae Lee, Lajanugen Logeswaran, Minjoon Seo. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

We study few-shot reranking for multi-hop QA (MQA) with open-domain questions.To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PROMPTRANK, which relies on language model prompting for multi-hop path reranking.PROMPTRANK first constructs an instruction-based prompt that includes a candidate document path and then computes the relevance score between a given question and the path based on the conditional likelihood of the question given the path prompt according to a language model.PROMPTRANK yields strong retrieval performance on HotpotQA with only 128 training examples compared to state-of-theart methods trained on thousands of examples -73.6 recall@10 by PROMPTRANK vs. 77.8 by PathRetriever (Asai et al., 2020) and 77.5 by multi-hop dense retrieval (Xiong et al., 2021).

Batch Normalization (BN) and its variants has been extensively studied for neural nets in various computer vision tasks, but relatively little work has been dedicated to studying the effect of BN in continual learning. To that end, we develop a new update patch for BN, particularly tailored for the exemplar-based class-incremental learning (CIL). The main issue of BN in CIL is the imbalance of training data between current and past tasks in a mini-batch, which makes the empirical mean and variance as well as the learnable affine transformation parameters of BN heavily biased toward the current task - contributing to the forgetting of past tasks. While one of the recent BN variants has been developed for” online” CIL; in which the training is done with a single epoch, we show that their method does not necessarily bring gains for “offline” CIL, in which a model is trained with multiple epochs on the imbalanced training data. The main reason for the ineffectiveness of their method lies in not fully addressing the data imbalance issue, especially in computing the gradients for learning the affine transformation parameters of BN. Accordingly, our new hyperparameter-free variant, dubbed as Task-Balanced BN (TBBN), is proposed to more correctly resolve the imbalance issue by making a horizontally-concatenated task-balanced batch using both reshape and repeat operations during training. Based on our experiments on class incremental learning of CIFAR-100, ImageNet-100, and five dissimilar task datasets, we demonstrate that our TBBN, which works exactly the same as the vanilla BN in the inference time, is easily applicable to most existing exemplar-based offline CIL algorithms and consistently outperforms other BN variants.

Open-domain question answering (QA) systems are often built with retrieval modules.However, retrieving passages from a given source is known to suffer from insufficient knowledge coverage.Alternatively, prompting large language models (LLMs) to generate contextual passages based on their parametric knowledge has been shown to improve QA performance.Yet, LLMs tend to "hallucinate" content that conflicts with the retrieved knowledge.Based on the intuition that answers supported by both sources are more likely to be correct, we propose COMBO, a Compatibility-Oriented knowledge Merging for Better Open-domain QA framework, to effectively leverage the two sources of information.Concretely, we match LLM-generated passages with retrieved counterparts into compatible pairs, based on discriminators trained with silver compatibility labels.Then a Fusionin-Decoder-based (Izacard and Grave, 2021b) reader model handles passage pairs to arrive at the final answer.Experiments show that COMBO outperforms competitive baselines on three out of four tested open-domain QA benchmarks.Further analysis reveals that our proposed framework demonstrates greater efficacy in scenarios with a higher degree of knowledge conflicts.

Pre-trained language models (PLMs) have shown impressive performance in various language tasks.However, they are prone to spurious correlations, and often generate illusory information.In real-world applications, PLMs should justify decisions with formalized, coherent reasoning chains, but this challenge remains under-explored.Cognitive psychology theorizes that humans are capable of utilizing fast and intuitive heuristic thinking to make decisions based on past experience, then rationalizing the decisions through slower and deliberative analytic reasoning.We incorporate these interlinked dual processes in fine-tuning and in-context learning with PLMs, applying them to two language understanding tasks that require coherent physical commonsense reasoning.We show that our proposed Heuristic-Analytic Reasoning (HAR) strategies drastically improve the coherence of rationalizations for model decisions, yielding state-of-the-art results on Tiered Reasoning for Intuitive Physics (TRIP).We also find that this improved coherence is a direct result of more faithful attention to relevant language context in each step of reasoning.Our findings suggest that human-like reasoning strategies can effectively improve the coherence and reliability of PLM reasoning.

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown capabilities to generalize to unseen tasks. Previous work has shown that scaling the number of finetuning datasets and instructions is the key component in making stronger MT LMs. In this work, we report surprising findings that show an expert LM trained on just a single task can outperform an MT LM trained with 300+ different tasks on 11 different unseen datasets and on 13 datasets of the BIG-bench benchmark by an average of 3.20% and 1.29%, respectively. This finding casts doubt on the previously held belief that simply scaling the number of tasks makes stronger MT LMs. Leveraging this finding, we further show that this distributed approach of training multiple expert LMs instead of a single MT LM for zero-shot inference possesses many benefits including (1) avoiding negative task transfer that often occurs during instruction tuning, (2) being able to continually learn new tasks without having to re-train on previous tasks to avoid catastrophic forgetting, and (3) showing compositional capabilities when merging individual experts together.

Reasoning is the crux of intellectual thinking. While question answering (QA) tasks are prolific with various computational models and benchmark datasets, they mostly tackle factoid or shallow QA without asking deeper understanding. Dual process theory asserts that human reasoning consists of associative thinking to collect relevant pieces of knowledge and logical reasoning to consciously conclude grounding on evidential rationale. Based on our intensive think-aloud study that revealed the three types of questions: surface, testing, and deep questions, we first propose the QASA benchmark that consists of 1798 novel question answering pairs that require full-stack reasoning on scientific articles in AI and ML fields. Then we propose the QASA approach that tackles the full-stack reasoning with large language models via associative selection, evidential rationale-generation, and systematic composition. Our experimental results show that QASA's full-stack inference outperforms the state-of-the-art InstructGPT by a big margin. We also find that rationale-generation is critical for the performance gain, claiming how we should rethink advanced question answering. The dataset is available at https://github.com/lgresearch/QASA.

Modeling spatiotemporal dynamics with neural differential equations has become a major line of research that opens new ways to handle various real-world scenarios (e.g., missing observations, irregular times, etc.). Despite such progress, most existing methods still face challenges in providing a general framework for analyzing time series. To tackle this, we adopt stochastic differential games to suggest a new philosophy of utilizing interacting collective intelligence in time series analysis. For the implementation, we develop the novel gradient descent-based algorithm called deep neural fictitious play to approximate the Nash equilibrium. We theoretically analyze the convergence result of the proposed algorithm and discuss the advantage of cooperative games in handling noninformative observation. Throughout the experiments on various datasets, we demonstrate the superiority of our framework over all the tested benchmarks in modeling time-series prediction by capitalizing on the advantages of applying cooperative games. An ablation study shows that neural agents of the proposed framework learn intrinsic temporal relevance to make accurate time-series predictions.

Novelty detection is a fundamental task of machine learning which aims to detect abnormal (*i.e.* out-of-distribution (OOD)) samples. Since diffusion models have recently emerged as the de facto standard generative framework with surprising generation results, novelty detection via diffusion models has also gained much attention. Recent methods have mainly utilized the reconstruction property of in-distribution samples. However, they often suffer from detecting OOD samples that share similar background information to the in-distribution data. Based on our observation that diffusion models can *project* any sample to an in-distribution sample with similar background information, we propose *Projection Regret (PR)*, an efficient novelty detection method that mitigates the bias of non-semantic information. To be specific, PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Since the perceptual distance often fails to capture semantic changes when the background information is dominant, we cancel out the background bias by comparing it against recursive projections. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.

We consider offline safe imitation learning (IL), where the agent aims to learn the safe policy that mimics preferred behavior while avoiding non-preferred behavior from non-preferred demonstrations and unlabeled demonstrations. This problem setting corresponds to various real-world scenarios, where satisfying safety constraints is more important than maximizing the expected return. However, it is very challenging to learn the policy to avoid constraint-violating (i.e. non-preferred) behavior, as opposed to standard imitation learning which learns the policy to mimic given demonstrations. In this paper, we present a hyperparameter-free offline safe IL algorithm, SafeDICE, that learns safe policy by leveraging the non-preferred demonstrations in the space of stationary distributions. Our algorithm directly estimates the stationary distribution corrections of the policy that imitate the demonstrations excluding the non-preferred behavior. In the experiments, we demonstrate that our algorithm learns a more safe policy that satisfies the cost constraint without degrading the reward performance, compared to baseline algorithms.

Computational chemistry aims to autonomously design specific molecules with target functionality. Generative frameworks provide useful tools to learn continuous representations of molecules in a latent space. While modelers could optimize chemical properties, many generated molecules are not synthesizable. To design synthetically accessible molecules that preserve main structural motifs of target molecules, we propose a reaction-embedded and structure-conditioned variational autoencoder. As the latent space jointly encodes molecular structures and their reaction routes, our new sampling method that measures the path-informed structural similarity allows us to effectively generate structurally analogous synthesizable molecules. When targeting out-of-domain as well as in-domain seed structures, our model generates structurally and property-wisely similar molecules equipped with well-defined reaction paths. By focusing on the important region in chemical space, we also demonstrate that our model can design new molecules with even higher activity than the seed molecules.

Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under a hand-crafted patterns and 2) full attention followed by a sparse variant of softmax such as $\alpha$-entmax. Unfortunately, the first group lacks adaptability to data while the second still requires quadratic cost in training. In this work, we propose SBM-Transformer, a model that resolves both problems by endowing each attention head with a mixed-membership Stochastic Block Model (SBM). Then, each attention head data-adaptively samples a bipartite graph, the adjacency of which is used as an attention mask for each input. During backpropagation, a straight-through estimator is used to flow gradients beyond the discrete sampling step and adjust the probabilities of sampled edges based on the predictive loss. The forward and backward cost are thus linear to the number of edges, which each attention head can also choose flexibly based on the input. By assessing the distribution of graphs, we theoretically show that SBM-Transformer is a universal approximator for arbitrary sequence-to-sequence functions in expectation. Empirical evaluations under the LRA and GLUE benchmarks demonstrate that our model outperforms previous efficient variants as well as the original Transformer with full attention. Our implementation can be found in https://github.com/sc782/SBM-Transformer.

Optical Chemical Structure Recognition (OCSR) deals with the translation from chemical images to molecular structures, this being the main way chemical compounds are depicted in scientific documents. Traditionally, rule-based methods have followed a framework based on the detection of chemical entities, such as atoms and bonds, followed by a compound structure reconstruction step. Recently, neural architectures analog to image captioning have been explored to solve this task, yet they still show to be data inefficient, using millions of examples just to show performances comparable with traditional methods. Looking to motivate and benchmark new approaches based on atomic-level entities detection and graph reconstruction, we present CEDe, a unique collection of chemical entity bounding boxes manually curated by experts for scientific literature datasets. These annotations combine to more than 700,000 chemical entity bounding boxes with the necessary information for structure reconstruction. Also, a large synthetic dataset containing one million molecular images and annotations is released in order to explore transfer-learning techniques that could help these architectures perform better under low-data regimes. Benchmarks show that detection-reconstruction based models can achieve performances on par with or better than image captioning-like models, even with 100x fewer training examples.

Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources. In this paper, we propose a method (BeamCLIP) that can effectively transfer the representations of a large pre-trained multimodal model (CLIP-ViT) into a small target model (e.g., ResNet-18). For unsupervised transfer, we introduce cross-modal similarity matching (CSM) that enables a student model to learn the representations of a teacher model by matching the relative similarity distribution across text prompt embeddings. To better encode the text prompts, we design context-based prompt augmentation (CPA) that can alleviate the lexical ambiguity of input text prompts. Our experiments show that unsupervised representation transfer of a pre-trained vision-language model enables a small ResNet-18 to achieve a better ImageNet-1K top-1 linear probe accuracy (66.2%) than vision-only self-supervised learning (SSL) methods (e.g., SimCLR: 51.8%, SwAV: 63.7%), while closing the gap with supervised learning (69.8%).

We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat all nodes and edges as independent tokens, augment them with token embeddings, and feed them to a Transformer. With an appropriate choice of token embeddings, we prove that this approach is theoretically at least as expressive as an invariant graph network (2-IGN) composed of equivariant linear layers, which is already more expressive than all message-passing Graph Neural Networks (GNN). When trained on a large-scale graph dataset (PCQM4Mv2), our method coined Tokenized Graph Transformer (TokenGT) achieves significantly better results compared to GNN baselines and competitive results compared to Transformer variants with sophisticated graph-specific inductive bias. Our implementation is available at https://github.com/jw9730/tokengt.

Across many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative. By transforming unsupervised learning problems into decompositions of co-occurrence statistics, spectral algorithms provide transparent and efficient algorithms for posterior inference such as latent topic analysis and community detection. As object vocabularies grow, however, it becomes rapidly more expensive to store and run inference algorithms on co-occurrence statistics. Rectifying co-occurrence, the key process to uphold model assumptions, becomes increasingly more vital in the presence of rare terms, but current techniques cannot scale to large vocabularies. We propose novel methods that simultaneously compress and rectify co-occurrence statistics, scaling gracefully with the size of vocabulary and the dimension of latent space. We also present new algorithms learning latent variables from the compressed statistics, and verify that our methods perform comparably to previous approaches on both textual and non-textual data.

Spectral algorithms operate on matrices or tensors of word co-occurrence to learn latent topics. These approaches remove the dependence on the original documents and produce substantial gains in efficiency with provable inference, but at a cost: the models can no longer infer any information about individual documents. Thresholded Linear Inverse is developed to learn document-specific topic compositions, but its linear characteristics limit the inference quality without considering any prior information on topic distributions. We propose two novel estimation methods that respect previously unclear prior structures of spectral topic models. Experiments on a variety of synthetic to real collections demonstrate that our Prior-Aware Dual Decomposition outperforms the baseline method, whereas our Prior-Aware Manifold Iteration performs even better on short realistic data.

Moontae Lee, Sungjun Cho, David Bindel, David Mimno. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Many online communities present user-contributed responses, such as reviews of products and answers to questions. User-provided helpfulness votes can highlight the most useful responses, but voting is a social process that can gain momentum based on the popularity of responses and the polarity of existing votes. We propose the Chinese Voting Process (CVP) which models the evolution of helpfulness votes as a self-reinforcing process dependent on position and presentation biases. We evaluate this model on Amazon product reviews and more than 80 StackExchange forums, measuring the intrinsic quality of individual responses and behavioral coefficients of different communities.

Spectral inference provides fast algorithms and provable optimality for latent topic analysis. But for real data these algorithms require additional ad-hoc heuristics, and even then often produce unusable results. We explain this poor performance by casting the problem of topic inference in the framework of Joint Stochastic Matrix Factorization (JSMF) and showing that previous methods violate the theoretical conditions necessary for a good solution to exist. We then propose a novel rectification method that learns high quality topics and their interactions even on small, noisy data. This method achieves results comparable to probabilistic techniques in several domains while maintaining scalability and provable optimality.

The anchor words algorithm performs provably efficient topic model inference by finding an approximate convex hull in a high-dimensional word co-occurrence space.However, the existing greedy algorithm often selects poor anchor words, reducing topic quality and interpretability.Rather than finding an approximate convex hull in a high-dimensional space, we propose to find an exact convex hull in a visualizable 2-or 3-dimensional space.Such low-dimensional embeddings both improve topics and clearly show users why the algorithm selects certain words.

People complete tasks more quickly when they have concrete plans. However, they often fail to create such action plans. (How) can systems provide these concrete steps automatically? This article demonstrates that these benefits can also be realized when these plans are created by others or reused from similar tasks. Four experiments test these approaches, finding that people indeed complete more tasks when they receive externally-created action plans. To automatically provide plans, we introduce the Genies workflow that combines benefits of crowd wisdom, collaborative refinement, and automation. We demonstrate and evaluate this approach through the TaskGenies system, and introduce an NLP similarity algorithm for reusing plans. We demonstrate that it is possible for people to create action plans for others, and we show that it can be cost effective.