Related papers: Sequence-Level Certainty Reduces Hallucination In …

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…

Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery but pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs that may…

This paper examines how to make large language models reliable for high-stakes legal work by reducing hallucinations. It distinguishes three AI paradigms: (1) standalone generative models ("creative oracle"), (2) basic retrieval-augmented…

Recent advancements in multimodal large language models have enhanced document understanding by integrating textual and visual information. However, existing models exhibit incompleteness within their paradigm in real-world scenarios,…

We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or…

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs) by providing access to external knowledge. However, current research primarily focuses on retrieval quality, often overlooking the critical…

Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly expressing uncertainty. We study whether prompt-only interventions --…

Large Language Models (LLMs) excel in many NLP tasks but remain prone to hallucinations, limiting trust in real-world applications. We present HalluGuard, a 4B-parameter Small Reasoning Model (SRM) for mitigating hallucinations in…

Achieving the right amount of trust in AI systems is important, but challenging. The problem is exacerbated with the rise of Large Language Models (LLMs) as they provide human-level communication capabilities, but potentially hallucinate in…

Common evaluation paradigms for language models focus on scoring single responses through accuracy metrics or proper scoring rules, failing to capture the full richness of a model's belief state. Recent work illustrates that language models…

Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucinations-generating content that is inconsistent with the input image. Existing training-free hallucination mitigation methods…

Retrieval-Augmented Generation (RAG) grounds language models in factual evidence but introduces critical challenges regarding knowledge conflicts between internalized parameters and retrieved information. However, existing reliability…

Language models (LMs) are known to suffer from hallucinations and misinformation. Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowledge corpus to complement the parametric knowledge in LMs…

Sentence-level relation extraction aims to identify the relation between two entities for a given sentence. The existing works mostly focus on obtaining a better entity representation and adopting a multi-label classifier for relation…

In real-world applications, Large Language Models (LLMs) often hallucinate, even in Retrieval-Augmented Generation (RAG) settings, which poses a significant challenge to their deployment. In this paper, we introduce AggTruth, a method for…

This study addresses the critical challenge of hallucination mitigation in Large Vision-Language Models (LVLMs) for Visual Question Answering (VQA) tasks through a Split Conformal Prediction (SCP) framework. While LVLMs excel in multi-modal…

Knowledge graphs (KGs), which could provide essential relational information between entities, have been widely utilized in various knowledge-driven applications. Since the overall human knowledge is innumerable that still grows explosively…

Uncertainty estimation is a promising approach to detect hallucinations in large language models (LLMs). Recent approaches commonly depend on model internal states to estimate uncertainty. However, they suffer from strict assumptions on how…

The goal of knowledge graph completion (KGC) is to predict missing facts among entities. Previous methods for KGC re-ranking are mostly built on non-generative language models to obtain the probability of each candidate. Recently,…

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,…