相关论文: TRACE: Trajectory Correction from Cross-layer Evid…

Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By…

LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections…

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical…

Large language models (LLMs) demonstrate strong capabilities in natural language processing but remain prone to hallucinations, generating factually incorrect or fabricated content. This issue undermines their reliability, particularly in…

Although large Language Models (LLMs) have achieved remarkable success, their practical application is often hindered by the generation of non-factual content, which is called "hallucination". Ensuring the reliability of LLMs' outputs is a…

Large language models hallucinate during multi-step reasoning, but most existing detectors operate at the trace level: they assign one confidence score to a full output, fail to localize the first error, and often require multiple sampled…

Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallucination detection requires disentangling the contributions…

Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing…

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for…

Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing mitigation methods typically treat hallucination as a uniform…

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make…

With the large-scale adoption of Large Language Models (LLMs) in various applications, there is a growing reliability concern due to their tendency to generate inaccurate text, i.e. hallucinations. In this work, we propose Cross-Layer…

We propose a novel single-step training strategy that allows convolutional encoder-decoder networks that use skip connections, to complete partially observed data by means of hallucination. This strategy is demonstrated for the task of…

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself…

Hallucinations are one of the major issues affecting LLMs, hindering their wide adoption in production systems. While current research solutions for detecting hallucinations are mainly based on heuristics, in this paper we introduce a…

Large Language Models (LLMs) excel in language comprehension and generation but are prone to hallucinations, producing factually incorrect or unsupported outputs. Retrieval Augmented Generation (RAG) systems address this issue by grounding…

Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we…

Retrieval Augmented Generation (RAG) systems remain vulnerable to hallucinated answers despite incorporating external knowledge sources. We present LettuceDetect a framework that addresses two critical limitations in existing hallucination…

Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace contribute very unevenly, and selecting reasoning data well requires assessing them…

Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their…