相关论文: ReBeCA: Unveiling Interpretable Behavior Hierarchy…

Large language models produce rich introspective language when prompted for self-examination, but whether this language reflects internal computation or sophisticated confabulation has remained unclear. We show that self-referential…

Psychosocial constructs can only be assessed indirectly, and measures are typically formed by a combination of indicators that are thought to relate to the construct. Reflective and formative measurement models offer different…

Despite the growing reasoning capabilities of recent large language models (LLMs), their internal mechanisms during the reasoning process remain underexplored. Prior approaches often rely on human-defined concepts (e.g., overthinking,…

Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle multi-agent coordination, and inefficient test-time scaling…

Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The…

Reward models play a fundamental role in aligning large language models with human preferences. Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and…

Instruction-based suppression is widely used to prevent language models from generating prohibited content, yet it remains unclear whether suppression reduces internal representation or merely suppresses expression. We investigate this…

Large Language Models (LLMs) agents are increasingly pivotal for addressing complex tasks in interactive environments. Existing work mainly focuses on enhancing performance through behavior cloning from stronger experts, yet such approaches…

Large Language Model interfaces are increasingly verbose, exposing intermediate reasoning traces alongside final answers. Traces are framed as transparency mechanisms, yet it is unclear how people use them to solve problems. We report a…

Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models…

Interpretability is a pressing issue for decision systems. Many post hoc methods have been proposed to explain the predictions of a single machine learning model. However, business processes and decision systems are rarely centered around a…

Large reasoning models excel in domains like mathematics where intermediate reasoning is straightforward to verify, but struggle to self-correct in medicine fields where evaluating intermediate reasoning is cumbersome and expensive. This…

Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating…

Evaluating competing systems in a comparable way, i.e., benchmarking them, is an undeniable pillar of the scientific method. However, system performance is often summarized via a small number of metrics. The analysis of the evaluation…

The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning…

Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as…

Recent advances in explainable recommendations have explored the integration of language models to analyze natural language rationales for user-item interactions. Despite their potential, existing methods often rely on ID-based…

As robotic technology rapidly develops, robots are being employed in an increasing number of fields. However, due to the complexity of deployment environments or the prevalence of ambiguous-condition objects, the practical application of…

Understanding how humans process natural language has long been a vital research direction. The field of natural language processing (NLP) has recently experienced a surge in the development of powerful language models. These models have…

Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public trust. Existing toxicity mitigation approaches primarily…