English
Related papers

Related papers: Steer LLM Latents for Hallucination Detection

200 papers

Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Meng Shen , Minghao Wu , Deepu Rajan

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…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Tsung-Han Wu , Heekyung Lee , Jiaxin Ge , Joseph E. Gonzalez , Trevor Darrell , David M. Chan

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zhe Cheng , Wenyu Chen , Fode Zhang , Dehuan Shen

A common approach to hallucination detection casts it as a natural language inference (NLI) task, often using LLMs to classify whether the generated text is entailed by corresponding reference texts. Since entailment classification is a…

Computation and Language · Computer Science 2025-06-06 Ron Eliav , Arie Cattan , Eran Hirsch , Shahaf Bassan , Elias Stengel-Eskin , Mohit Bansal , Ido Dagan

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Computation and Language · Computer Science 2026-03-03 Haolei Xu , Xinyu Mei , Yuchen Yan , Rui Zhou , Wenqi Zhang , Weiming Lu , Yueting Zhuang , Yongliang Shen

Large Audio-Language Models and Multi-Modal Large Language Models have demonstrated strong capabilities in tasks such as Audio Question Answering (AQA), Audio Captioning, and Automatic Speech Recognition (ASR). However, there is growing…

Sound · Computer Science 2025-10-16 Tsung-En Lin , Kuan-Yi Lee , Hung-Yi Lee

Multi-modal Large Language Models (MLLMs) have emerged as a powerful paradigm for integrating visual and textual information, supporting a wide range of multi-modal tasks. However, these models often suffer from hallucination, producing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Zhiyuan Chen , Yuecong Min , Jie Zhang , Bei Yan , Jiahao Wang , Xiaozhen Wang , Shiguang Shan

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

Machine Learning · Computer Science 2025-10-07 Hazel Kim , Tom A. Lamb , Adel Bibi , Philip Torr , Yarin Gal

Hallucinations in large language model (LLM) outputs severely limit their reliability in knowledge-intensive tasks such as question answering. To address this challenge, we introduce REFIND (Retrieval-augmented Factuality hallucINation…

Computation and Language · Computer Science 2025-04-09 DongGeon Lee , Hwanjo Yu

Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination Assessment via Log-probs as Time series), a lightweight hallucination detector that leverages…

Computation and Language · Computer Science 2026-02-04 Ahmad Shapiro , Karan Taneja , Ashok Goel

Hallucinations pose a significant challenge to the reliability of large vision-language models, making their detection essential for ensuring accuracy in critical applications. Current detection methods often rely on computationally…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Eunkyu Park , Minyeong Kim , Gunhee Kim

Large Vision-Language Models (LVLMs) have made remarkable developments along with the recent surge of large language models. Despite their advancements, LVLMs have a tendency to generate plausible yet inaccurate or inconsistent information…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Dexter Neo , Tsuhan Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is…

Computation and Language · Computer Science 2025-05-23 Fujie Zhang , Peiqi Yu , Biao Yi , Baolei Zhang , Tong Li , Zheli Liu

Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently "hallucinate," resulting in non-factual outputs. Our carefully-designed human evaluation…

Computation and Language · Computer Science 2024-03-22 Jian Guan , Jesse Dodge , David Wadden , Minlie Huang , Hao Peng

Large vision-language models (LVLMs) achieve strong multimodal performance, but still suffer from hallucinations caused by unstable visual grounding and over-reliance on language priors. Existing training-free decoding methods typically…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Xinyun Liu

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such…

Machine Learning · Computer Science 2025-11-04 Jayneel Parekh , Pegah Khayatan , Mustafa Shukor , Arnaud Dapogny , Alasdair Newson , Matthieu Cord

We investigate the internal representations of vision-language models (VLMs) to address hallucinations, a persistent challenge despite advances in model size and training. We project VLMs' internal image representations to their language…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Nick Jiang , Anish Kachinthaya , Suzie Petryk , Yossi Gandelsman

Neural network pruning has emerged as a promising approach for deploying LLMs in low-resource scenarios while preserving downstream task performance. However, for the first time, we reveal that such pruning disrupts LLMs' internal…

Machine Learning · Computer Science 2025-09-04 Yao Fu , Runchao Li , Xianxuan Long , Haotian Yu , Xiaotian Han , Yu Yin , Pan Li

Despite their vast capabilities, Large Language Models (LLMs) often struggle with generating reliable outputs, frequently producing high-confidence inaccuracies known as hallucinations. Addressing this challenge, our research introduces…

Computation and Language · Computer Science 2024-06-19 Mohammad Beigi , Ying Shen , Runing Yang , Zihao Lin , Qifan Wang , Ankith Mohan , Jianfeng He , Ming Jin , Chang-Tien Lu , Lifu Huang

Large Language Models (LLMs) driven by In-Context Learning (ICL) have significantly improved the performance of text-to-SQL. Previous methods generally employ a two-stage reasoning framework, namely 1) schema linking and 2) logical…

Computation and Language · Computer Science 2024-05-27 Ge Qu , Jinyang Li , Bowen Li , Bowen Qin , Nan Huo , Chenhao Ma , Reynold Cheng