相关论文: Detection Without Correction: A Robust Asymmetry i…

We find that correct-to-incorrect sycophancy signals are most linearly separable within multi-head attention activations. Motivated by the linear representation hypothesis, we train linear probes across the residual stream, multilayer…

We identify a previously unknown calibration property of large language models: providing one confirmed intermediate fact toward a multi-step reasoning chain increases the model's confident-wrong-answer rate before full evidence eliminates…

Hallucinations present a significant challenge for large language models (LLMs). The utilization of parametric knowledge in generating factual content is constrained by the limited knowledge of LLMs, potentially resulting in internal…

Despite the remarkable ability of large vision-language models (LVLMs) in image comprehension, these models frequently generate plausible yet factually incorrect responses, a phenomenon known as hallucination.Recently, in large language…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio input. We analyze these grounding failures and identify a…

Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability. While existing hallucination detection methods achieve strong performance in question-answering tasks,…

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate,…

Multimodal language models can exhibit hallucinations in their outputs, which limits their reliability. The ability to automatically detect these errors is important for mitigating them, but has been less explored and existing efforts do…

Despite their impressive ability to generate high-quality and fluent text, generative large language models (LLMs) also produce hallucinations: statements that are misaligned with established world knowledge or provided input context.…

Large language models (LLMs) are prone to hallucinations, which sparked a widespread effort to detect and prevent them. Recent work attempts to mitigate hallucinations by intervening in the model's generation, typically computing…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

Although Large Language Models have demonstrated powerful capabilities in a wide range of tasks such as language understanding and code generation, the frequent occurrence of hallucinations during the generation process has become a…

Hallucination is a central failure mode in large language models (LLMs). We focus on hallucinations of answers to questions like: "Which instrument did Glenn Gould play?", but we ask these questions for synthetic entities that are unknown…

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent…

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing…

Detecting content that contradicts or is unsupported by a given source text is a critical challenge for the safe deployment of generative language models. We introduce HALT-RAG, a post-hoc verification system designed to identify…

We test whether a geometric hallucination taxonomy -- classifying failures as center-drift (Type~1), wrong-well convergence (Type~2), or coverage gaps (Type~3) -- can distinguish hallucination types through controlled induction in GPT-2.…

Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to…

Hallucinations in Large Language Models (LLMs), defined as the generation of content inconsistent with facts or context, represent a core obstacle to their reliable deployment in critical domains. Current research primarily focuses on…