Large Language Models (LLMs) have advanced rapidly and raised the bar for what AI is expected to do. However, accompanied with such progress is a stronger consensus that these models consistently fail in out-of-distribution reasoning, especially on tasks that require abstraction, transfer, or long-horizon planning. While acceptable for most consumer use, these issues prevent AI from being safely deployed in high-stakes settings (e.g., healthcare), where stakeholders cannot trust AI models that exhibit uncontrollable and unpredictable failures. In this talk, I will discuss our work and insights on how to make LLM reasoning controllable and trustworthy, by 1) understanding the mechanisms of LLM reasoning and predicting when LLM will fail; 2) improving model reasoning and generalization based on such insights; and 3) moving towards trustworthy AI applications through such improvements, and identifying new problems to form a healthy positive-feedback loop.

Recent advances in test-time scaling have led to the emergence of thinking LLMs that exhibit self-reflective behaviors and multi-step reasoning.While RL drives this self-improvement paradigm, a recent study (Gandhi et al., 2025) shows that RL alone does not truly instill these new reasoning abilities -it merely draws out behaviors already present in the base models.This raises a question: How can we train models that don't exhibit such thinking behavior to develop it in the first place?To this end, we propose THINKTUNING, a GRPO-based interactive training approach where we augment the rollouts of a student model with the guidance from a teacher model.A simple idea from classroom practice inspires our method: a teacher poses a problem, lets the student try an answer, then gives corrective feedback-enough to point the mind in the right direction and then show the solution.Each piece of feedback reshapes the student's thoughts, leading them to arrive at the correct solution.Similarly, we find that this type of implicit supervision through feedback from a teacher model of the same size improves the reasoning capabilities of the student model.In particular, on average, our method shows a 3.85% improvement over zero-shot baselines across benchmarks, and on MATH-500, AIME and GPQA-Diamond it shows 2.08%, 2.23% and 3.99% improvements over the vanilla-GRPO baseline 1 .

Predictive models often need to work with incomplete information in real-world tasks. Consequently, they must provide reliable probability or confidence estimation, especially in large-scale decision-making and planning tasks. Current large language models (LLMs) are insufficient for accurate estimations, but they can generate relevant factors that may affect the probabilities, produce coarse-grained probabilities when the information is more complete, and help determine which factors are relevant to specific downstream contexts. In this paper, we make use of these capabilities of LLMs to provide a significantly more accurate probabilistic estimation. We propose BIRD, a novel probabilistic inference framework that aligns a Bayesian network with LLM abductions and then estimates more accurate probabilities in a deduction step. We show BIRD provides reliable probability estimations that are 30% better than those provided directly by LLM baselines. These estimates further contribute to better and more trustworthy decision making.

Zhikun Xu, Ming Shen, Jacob Dineen, Zhaonan Li, Xiao Ye, Shijie Lu, Aswin Rrv, Chitta Baral, Ben Zhou. 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.

Sihao Chen, Hongming Zhang, Tong Chen, Ben Zhou, Wenhao Yu, Dian Yu, Baolin Peng, Hongwei Wang, Dan Roth, Dong Yu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Bangzheng Li, Ben Zhou, Fei Wang, Xingyu Fu, Dan Roth, Muhao Chen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Temporal reasoning is the task of predicting temporal relations of event pairs.While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems' generalizability due to existing datasets' limitations.In this work, we introduce a novel task named TODAY that bridges this gap with temporal differential analysis, which as the name suggests, evaluates whether systems can correctly understand the effect of incremental changes.Specifically, TODAY introduces slight contextual changes for given event pairs, and systems are asked to tell how this subtle contextual change would affect relevant temporal relation distributions.To facilitate learning, TODAY also annotates human explanations.We show that existing models, including GPT-3.5, drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions.On the other hand, we show that TODAY's supervision style and explanation annotations can be used in joint learning, encouraging models to use more appropriate signals during training and thus outperform across several benchmarks.TODAY can also be used to train models to solicit incidental supervision from noisy sources such as GPT-3.5, thus moving us more toward the goal of generic temporal reasoning systems.

Images are often more significant than only the pixels to human eyes, as we can infer, associate, and reason with contextual information from other sources to establish a more complete picture. For example, in Figure This reasoning could provide the time and place the image was taken, which will help us in subsequent tasks, such as automatic storyline construction, correction of image source in intended effect photographs, and upper-stream processing such as image clustering for certain location or time.

News events are often associated with quantities (e.g., the number of COVID-19 patients or the number of arrests in a protest), and it is often important to extract their type, time, and location from unstructured text in order to analyze these quantity events.This paper thus formulates the NLP problem of spatiotemporal quantity extraction, and proposes the first meta-framework for solving it.This meta-framework contains a formalism that decomposes the problem into several information extraction tasks, a shareable crowdsourcing pipeline, and transformer-based baseline models.We demonstrate the meta-framework in three domains-the COVID-19 pandemic, Black Lives Matter protests, and 2020 California wildfires-to show that the formalism is general and extensible, the crowdsourcing pipeline facilitates fast and high-quality data annotation, and the baseline system can handle spatiotemporal quantity extraction well enough to be practically useful.We release all resources for future research on this topic.1

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems.However, despite the many datasets and resources built as part of this effort, the majority have small-scale annotations and limited scope, which is insufficient to solve general decomposition tasks.In this paper, we look at large-scale intermediate pre-training of decomposition-based transformers using distant supervision from comparable texts, particularly large-scale parallel news.We show that with such intermediate pre-training, developing robust decomposition-based models for a diverse range of tasks becomes more feasible.For example, on semantic parsing, our model, DECOMPT5, improves 20% to 30% on two datasets, Overnight and TORQUE, over the baseline language model.We further use DECOMPT5 to build a novel decompositionbased QA system named DECOMPENTAIL, improving over state-of-the-art models, including GPT-3, on both HotpotQA and StrategyQA by 8% and 4%, respectively.

Speaker identification (SI) in texts aims to identify the speaker(s) for each utterance in texts.Previous studies divide SI into several sub-tasks (e.g., quote extraction, named entity recognition, gender identification, and coreference resolution).However, we are still far from solving these sub-tasks, making SI systems that rely on them seriously suffer from error propagation.End-to-end SI systems, on the other hand, are not limited by individual modules, but suffer from insufficient training data from the existing small-scale datasets.To make large end-to-end models possible, we design a new annotation guideline that regards SI as span extraction from the local context, and we annotate by far the largest SI dataset for Chinese named CSI based on eighteen novels.Viewing SI as a span extraction task also introduces the possibility of applying existing storng extractive machine reading comprehension (MRC) baselines.Surprisingly, simply using such a baseline without human-annotated character names and carefully designed rules, we can already achieve performance comparable or better than those of previous state-of-the-art SI methods on all public SI datasets for Chinese.Furthermore, we show that our dataset can serve as additional training data for existing benchmarks, which leads to further gains (up to 6.5% in accuracy).Finally, using CSI as a clean source, we design an effective self-training paradigm to continuously leverage hundreds of unlabeled novels.

Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagespecific KGs that refer to the same real-world object.Such methods are often hindered by the insufficiency of seed alignment provided between KGs.Therefore, we propose an incidentally supervised model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental supervision signals from text.JEANS first deploys an entity grounding process to combine each KG with the monolingual text corpus.Then, two learning processes are conducted: (i) an embedding learning process to encode the KG and text of each language in one embedding space, and (ii) a selflearning based alignment learning process to iteratively induce the matching of entities and that of lexemes between embeddings.Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision, and significantly outperforms state-of-the-art methods that solely rely on internal information of KGs. 1 * Indicating equal contributions.

Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, Dan Roth. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language.However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on such concepts is costly.This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TACOLM, 1 a temporal common sense language model.Our method is shown to give quality predictions of various dimensions of temporal common sense (on UDST and a newly collected dataset from Real-News).It also produces representations of events for relevant tasks such as duration comparison, parent-child relations, event coreference and temporal QA (on TimeBank, HiEVE and MCTACO) that are better than using the standard BERT.Thus, it will be an important component of temporal NLP.

Ben Zhou, Daniel Khashabi, Qiang Ning, Dan Roth. 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.

The problem of entity-typing has been studied predominantly in supervised learning fashion, mostly with task-specific annotations (for coarse types) and sometimes with distant supervision (for fine types).While such approaches have strong performance within datasets, they often lack the flexibility to transfer across text genres and to generalize to new type taxonomies.In this work we propose a zero-shot entity typing approach that requires no annotated data and can flexibly identify newly defined types.Given a type taxonomy defined as Boolean functions of FREEBASE "types", we ground a given mention to a set of type-compatible Wikipedia entries and then infer the target mention's types using an inference algorithm that makes use of the types of these entries.We evaluate our system on a broad range of datasets, including standard fine-grained and coarse-grained entity typing datasets, and also a dataset in the biological domain.Our system is shown to be competitive with state-of-theart supervised NER systems and outperforms them on out-of-domain datasets.We also show that our system significantly outperforms other zero-shot fine typing systems.