Related papers: ConciseRL: Conciseness-Guided Reinforcement Learni…

While Small Language Models (SLMs) have demonstrated promising performance on an increasingly wide array of commonsense reasoning benchmarks, current evaluation practices rely almost exclusively on the accuracy of their final answers,…

Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments,…

Recent advances in large language models have demonstrated the promise of unsupervised reinforcement learning (RL) methods for enhancing reasoning capabilities without external supervision. However, the generalizability of these label-free…

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured…

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably…

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an…

Retrieval-Augmented Generation (RAG) delivers substantial value in knowledge-intensive applications. However, its generated responses often lack transparent reasoning paths that trace back to source evidence from retrieved documents. This…

Large Language Models (LLMs) are fluent but prone to hallucinations, producing answers that appear plausible yet are unsupported by available evidence. This failure is especially problematic in high-stakes domains where decisions must be…

Recent Large Reasoning Language Models (LRLMs) employ long chain-of-thought reasoning with complex reflection behaviors, typically signaled by specific trigger words (e.g., "Wait" and "Alternatively") to enhance performance. However, these…

Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual understanding, most existing REC methods rely on rulebased…

Large Language Models (LLMs) have achieved impressive performance across a range of natural language processing tasks. However, recent advances demonstrate that further gains particularly in complex reasoning tasks require more than merely…

Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning…

Large Language Models (LLMs) have recently achieved remarkable progress by leveraging Reinforcement Learning and extended Chain-of-Thought (CoT) techniques. However, the challenge of performing efficient language reasoning--especially…

Robust evaluation is critical for deploying trustworthy retrieval-augmented generation (RAG) systems. However, current LLM-based evaluation frameworks predominantly rely on directly prompting resource-intensive models with complex…

Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general…

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…

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…