Related papers: Towards Generalizable Reasoning: Group Causal Coun…

Linear temporal logic (LTL) offers a simplified way of specifying tasks for policy optimization that may otherwise be difficult to describe with scalar reward functions. However, the standard RL framework can be too myopic to find maximally…

Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we…

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts,…

Causality is vital for understanding true cause-and-effect relationships between variables within predictive models, rather than relying on mere correlations, making it highly relevant in the field of Explainable AI. In an automated…

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces supervision on intermediate steps but…

While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive groups. Existing benchmarks effectively identify these biases,…

Prior research has demonstrated noticeable performance gains through the use of probabilistic tokenizations, an approach that involves employing multiple tokenizations of the same input string during the training phase of a language model.…

Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such…

Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-agent reinforcement learning (MARL), particularly in…

Causal reasoning is a core component of intelligence. Large language models (LLMs) have shown impressive capabilities in generating human-like text, raising questions about whether their responses reflect true understanding or statistical…

While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of…

LLMs can be unpredictable, as even slight alterations to the prompt can cause the output to change in unexpected ways. Thus, the ability of models to accurately explain their behavior is critical, especially in high-stakes settings. One…

Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual…

Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have…

While Large Language Models (LLMs) have demonstrated significant potential in natural language processing , complex general-purpose reasoning requiring multi-step logic, planning, and verification remains a critical bottleneck. Although…

Large Language Models (LLMs) have shown state-of-the-art performance in a variety of tasks, including arithmetic and reasoning; however, to gauge the intellectual capabilities of LLMs, causal reasoning has become a reliable proxy for…

Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…

Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data. While large language models (LLMs) have shown strong performance in biomedical NLP,…

While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision…