Related papers: SEER: Facilitating Structured Reasoning and Explan…

This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems based on dataset-driven insights. The traditional method for rule induction from data typically requires…

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning…

Although Large Audio-Language Models (LALMs) have exhibited outstanding performance in auditory understanding, their performance in affective computing scenarios, particularly in emotion recognition, reasoning, and subtle sentiment…

Despite remarkable advances in the field, LLMs remain unreliable in distinguishing causation from correlation. Recent results from the Corr2Cause dataset benchmark reveal that state-of-the-art LLMs -- such as GPT-4 (F1 score: 29.08) -- only…

Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retrievers often become the bottleneck of RAG systems due to…

Action chunking can improve exploration and value estimation in long horizon reinforcement learning, but makes learning substantially harder since the critic must evaluate action sequences rather than single actions, greatly increasing…

Chain-of-Thought (CoT) has become a cornerstone of reasoning in large language models, yet its effectiveness is constrained by the limited expressiveness of discrete token sampling. Recent latent reasoning approaches attempt to alleviate…

This extended abstract introduces Self-Explaining Contrastive Evidence Re-Ranking (CER), a novel method that restructures retrieval around factual evidence by fine-tuning embeddings with contrastive learning and generating token-level…

Reinforcement learning-based retrieval-augmented generation (RAG) methods enhance the reasoning abilities of large language models (LLMs). However, most rely only on final-answer rewards, overlooking intermediate reasoning quality. This…

State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased interest in designing more interpretable deep models for NLP…

Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar…

Query rewriting is essential for database performance optimization, but existing automated rule enumeration methods suffer from exponential search spaces, severe redundancy, and poor scalability, especially when handling complex query plans…

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

Large language models can produce correct answers while relying on flawed reasoning traces, partly because common training objectives reward final-answer correctness rather than faithful intermediate reasoning. This undermines…

Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively. Nevertheless, due to their limited capabilities in reasoning and search, their performance on multi-hop QA…

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like…

Reasoning in interactive problem solving scenarios requires models to construct reasoning threads that reflect user understanding and align with structured domain knowledge. However, current reasoning models often lack explicit semantic…

We present Searn, an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. Searn is a meta-algorithm that…

Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire…

Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple documents. An example question might be "What is the…