Active Geo-localization (AGL) is the task of localizing a goal, represented in various modalities (e.g., aerial images, ground-level images, or text), within a predefined search area. Current methods approach AGL as a goal-reaching reinforcement learning (RL) problem with a distance-based reward. They localize the goal by implicitly learning to minimize the relative distance from it. However, when distance estimation becomes challenging or when encountering unseen targets and environments, the agent exhibits reduced robustness and generalization ability due to the less reliable exploration strategy learned during training. In this paper, we propose GeoExplorer, an AGL agent that incorporates curiosity-driven exploration through intrinsic rewards. Unlike distance-based rewards, our curiosity-driven reward is goal-agnostic, enabling robust, diverse, and contextually relevant exploration based on effective environment modeling. These capabilities have been proven through extensive experiments across four AGL benchmarks, demonstrating the effectiveness and generalization ability of GeoExplorer in diverse settings, particularly in localizing unfamiliar targets and environments.

The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value of generative AI tools in many communities. However, the development of functional LLMs in many languages (i.e., multilingual LLMs) is bottlenecked by the lack of high-quality evaluation resources in languages other than English. Moreover, current practices in multilingual benchmark construction often translate English resources, ignoring the regional and cultural knowledge of the environments in which multilingual systems would be used. In this work, we construct an evaluation suite of 197,243 QA pairs from local exam sources to measure the capabilities of multilingual LLMs in a variety of regional contexts. Our novel resource, INCLUDE, is a comprehensive knowledge- and reasoning-centric benchmark across 44 written languages that evaluates multilingual LLMs for performance in the actual language environments where they would be deployed.

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship.However, data scarcity makes it challenging for language models to learn to generate commonsense inferences for contexts and questions involving interactions between complex events.To address this demand, we present COM 2 (COMplex COMmonsense), a new dataset created by sampling multi-hop logical queries (e.g., the joint effect or cause of both event A and B, or the effect of the effect of event C) from an existing commonsense knowledge graph (CSKG), and verbalizing them using handcrafted rules and large language models into multiple-choice and text generation questions.Our experiments show that language models trained on COM 2 exhibit significant improvements in complex reasoning ability, resulting in enhanced zero-shot performance in both indomain and out-of-domain tasks for question answering and generative commonsense reasoning, without expensive human annotations. 1* Work done during internship at EPFL. 1 Code and data are available at https://github.com/ tqfang/complex-commonsense-reasoning

Pretrained language models (LMs) encode implicit representations of knowledge in their parameters.However, localizing these representations and disentangling them from each other remains an open problem.In this work, we investigate whether pretrained language models contain various knowledge-critical subnetworks: particular sparse computational subgraphs that can, if removed, precisely suppress specific knowledge the model has memorized.We propose a multi-objective differentiable masking scheme that can be applied to both weights and neurons to discover such subnetworks and show that we can use them to precisely remove specific knowledge from models while minimizing adverse effects on the behavior of the original model.We demonstrate our method on multiple GPT2 variants, uncovering highly sparse subnetworks (98%+ sparsity) that are critical for expressing specific collections of relational knowledge.When these subnetworks are removed, the remaining network maintains most of its initial abilities but struggles to represent the suppressed knowledge.1

Models trained with counterfactually augmented data learn representations of the causal structure of tasks, enabling robust generalization.However, high-quality counterfactual data is scarce for most tasks and not easily generated at scale.When crowdsourced, such data is typically limited in scale and diversity; when generated using supervised methods, it is computationally expensive to extend to new counterfactual dimensions.In this work, we introduce DISCO (DIStilled COunterfactual Data), a new method for automatically generating highquality counterfactual data at scale.DISCO engineers prompts to generate phrasal perturbations with a large general language model.Then, a task-specific teacher model filters these generations to distill high-quality counterfactual data.While task-agnostic, we apply our pipeline to the task of natural language inference (NLI) and find that on challenging evaluations such as the NLI stress test, comparatively smaller student models trained with DISCOgenerated counterfactuals are more robust (6% absolute) and generalize better across distributions (2%) compared to models trained without data augmentation.Furthermore, DISCOaugmented models are 10% more consistent between counterfactual pairs on three evaluation sets, demonstrating that DISCO augmentation enables models to more reliably learn causal representations.Our

Various design settings for in-context learning (ICL), such as the choice and order of the incontext examples, can bias the model's predictions.While many studies discuss these design choices, there have been few systematic investigations into categorizing them and mitigating their impact.In this work, we define a typology for three types of label biases in ICL for text classification: vanilla-label bias, contextlabel bias, and domain-label bias (which we conceptualize and detect for the first time).Our analysis demonstrates that prior label bias calibration methods fall short of addressing all three types of biases.Specifically, domainlabel bias restricts LLMs to random-level performance on many tasks regardless of the choice of in-context examples.To mitigate the effect of these biases, we propose a simple bias calibration method that estimates a language model's label bias using random indomain words from the task corpus.After controlling for this estimated bias when making predictions, our novel domain-context calibration significantly improves the ICL performance of GPT-J and GPT-3 on a wide range of tasks.The gain is substantial on tasks with large domain-label bias (up to 37% in Macro-F1).Furthermore, our results generalize to models with different scales, pretraining methods, and manually-designed task instructions, showing the prevalence of label biases in ICL.

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered for a particular question, in-context reasoning can be sensitive to distractor facts, additional content that is irrelevant to a question but that may be relevant for a different question (i.e., not necessarily random noise). In these situations, the model fails to distinguish the necessary knowledge to answer the question, leading to spurious reasoning and degraded performance. This reasoning failure contrasts with the model’s apparent ability to distinguish its contextual knowledge from all the knowledge it has memorized during pre-training. Following this observation, we propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model’s parameters before presenting it with a question. Our method, RECKONING, is a bi-level learning algorithm that teaches language models to reason by updating their parametric knowledge through back-propagation, allowing them to answer questions using the updated parameters. During training, the inner loop rapidly adapts a copy of the model weights to encode contextual knowledge into its parameters. In the outer loop, the model learns to use the updated weights to reproduce and answer reasoning questions about the memorized knowledge. Our experiments on three diverse multi-hop reasoning datasets show that RECKONING’s performance improves over the in-context reasoning baseline (by up to 4.5%). We also find that compared to in-context reasoning, RECKONING generalizes better to longer reasoning chains unseen during training, is more robust to distractors in the context, and is computationally more efficient when multiple questions are asked about the same knowledge.

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties encoded in their contextualized representations. However, it is unclear whether they encode semantic knowledge that is crucial to symbolic inference methods. We propose a methodology for probing knowledge for inference that logical systems require but often lack in pre-trained language model representations. Our probing datasets cover a list of key types of knowledge used by many symbolic inference systems. We find that (i) pre-trained language models do encode several types of knowledge for inference, but there are also some types of knowledge for inference that are not encoded, (ii) language models can effectively learn missing knowledge for inference through fine-tuning. Overall, our findings provide insights into which aspects of knowledge for inference language models and their pre-training procedures capture. Moreover, we have demonstrated language models' potential as semantic and background knowledge bases for supporting symbolic inference methods.

In the age of large transformer language models, linguistic evaluation play an important role in diagnosing models' abilities and limitations on natural language understanding.However, current evaluation methods show some significant shortcomings.In particular, they do not provide insight into how well a language model captures distinct linguistic skills essential for language understanding and reasoning.Thus they fail to effectively map out the aspects of language understanding that remain challenging to existing models, which makes it hard to discover potential limitations in models and datasets.In this paper, we introduce CUR-RICULUM as a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena.CURRICULUM contains a collection of datasets that covers 36 types of major linguistic phenomena and an evaluation procedure for diagnosing how well a language model captures reasoning skills for distinct types of linguistic phenomena.We show that this linguisticphenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality.In addition, our experiments provide insight into the limitation of existing benchmark datasets and state-of-the-art models that may encourage future research on re-designing datasets, model architectures, and learning objectives. 1 .