相关论文: When Contextual Inference Fails: Cancelability in …

As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely…

Physical reasoning remains a significant challenge for Vision-Language Models (VLMs). This limitation arises from an inability to translate learned knowledge into predictions about physical behavior. Although continual fine-tuning can…

Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind queries and predictions is important when assessing how the learner works and, in turn, trust.…

The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple calibration, asking whether the language generated by the model…

Language models have recently achieved strong performance across a wide range of NLP benchmarks. However, unlike benchmarks, real world tasks are often poorly specified, and agents must deduce the user's intended behavior from a combination…

Recent work has examined language models from a linguistic perspective to better understand how they acquire language. Most existing benchmarks focus on judging grammatical acceptability, whereas the ability to interpret meanings conveyed…

Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined…

The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, these models are often treated as black boxes, with limited systematic investigation of their…

Training Large Language Models (LLMs) to follow user instructions has been shown to supply the LLM with ample capacity to converse fluently while being aligned with humans. Yet, it is not completely clear how an LLM can lead a plan-grounded…

While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliability. Consolidating agent consistency requires distilling trial-error trajectories into…

With state-of-the-art models achieving high performance on standard benchmarks, contemporary research paradigms continue to emphasize general intelligence as an enduring objective. However, this pursuit overlooks the fundamental disparities…

While large language models have shown impressive capabilities across a wide range of domains, they still encounter significant challenges in reasoning tasks that require gathering evidence over multiple turns and drawing logical…

The growing capabilities of Large Language Models (LLMs) have led to their widespread adoption for function completion within code repositories. Recent studies on such tasks show promising results when explicit instructions, often in the…

Schema-guided reasoning pipelines ask LLMs to produce explicit intermediate structures -- rubrics, checklists, verification queries -- before committing to a final decision. But do these structures causally determine the output, or merely…

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

To avoid the "meaning conflation deficiency" of word embeddings, a number of models have aimed to embed individual word senses. These methods at one time performed well on tasks such as word sense induction (WSI), but they have since been…

Explainable recommender systems are designed to elucidate the explanation behind each recommendation, enabling users to comprehend the underlying logic. Previous works perform rating prediction and explanation generation in a multi-task…

Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric models. We present the first mechanistic interpretability (MI)…

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…

Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering. However, outputs of these models rarely…