相关论文: Learning to Reason for Factuality

Large Language Models (LLMs), particularly slow-thinking models, often exhibit severe hallucination, outputting incorrect content due to an inability to accurately recognize knowledge boundaries during reasoning. While Reinforcement…

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric…

Large Language Models (LLMs) are trained on vast and diverse internet corpora that often include inaccurate or misleading content. Consequently, LLMs can generate misinformation, making robust fact-checking essential. This review…

While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical trade-off between capability and reliability. This work…

Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization, achieving impressive capabilities across various challenging benchmarks. However, our empirical analysis reveals a…

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly improved the performance of Large Language Models (LLMs) on tasks requiring multi-step reasoning. However, most RLVR pipelines rely on sparse outcome-based rewards,…

Claim verification with large language models (LLMs) has recently attracted growing attention, due to their strong reasoning capabilities and transparent verification processes compared to traditional answer-only judgments. However,…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation. Existing approaches for detecting hallucination in long-form…

Large Language Models (LLMs) have recently demonstrated strong potential in generating 'believable human-like' behavior in web environments. Prior work has explored augmenting training data with LLM-synthesized rationales and applying…

Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs. Existing approaches synthesize shorter reasoning responses for LRMs…

Hallucination in large language models (LLMs) during long-form generation remains difficult to address under existing reinforcement learning from human feedback (RLHF) frameworks, as their preference rewards often overlook the model's own…

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major…

As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings. However, they are prone to faithfulness hallucinations,…

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

The propensity of Large Language Models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains, where rigorous control over Type I errors (the conditional probability of incorrectly…

Mathematical reasoning is a central challenge for large language models (LLMs), requiring not only correct answers but also faithful reasoning processes. Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising…

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…