Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals (2026.acl-srw)
Copied to clipboard
| Challenge: | Existing methods conflate fluency with correctness or require substantial computational overhead. |
| Approach: | They propose a single-pass uncertainty quantification method that uses attention matrices to estimate uncertainty without requiring repeated sampling or external models. |
| Outcome: | The proposed method performs well across multiple datasets, task types, and model families and is highly predictive of answer correctness. |
Similar Papers
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods, such as a n-terminal coding, do not provide accurate data for large language models. |
| Approach: | They propose a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding. |
| Outcome: | Experiments on open-book QA datasets show that DAGCD improves faithfulness and robustness while preserving computational efficiency. |
Uncertainty Quantification for Large Language Models (2025.acl-tutorials)
Copied to clipboard
| Challenge: | Large language models (LLMs) produce hallucinations, which undermine user trust and reliability. |
| Approach: | This tutorial offers the first systematic introduction to uncertainty quantification (UQ) for LLMs in text generation tasks. |
| Outcome: | The proposed framework provides tools for communicating the reliability of a model answer. |
Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus (2023.emnlp-main)
Copied to clipboard
Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu
| Challenge: | Existing methods for detecting hallucinations in LLMs rely on external knowledge for reference retrieval or require sampling multiple responses for consistency verification. |
| Approach: | They propose a reference-free, uncertainty-based method for detecting hallucinations in Large Language Models that imitates human focus in factuality checking from three aspects: focus on the most informative keywords; focus on unreliable tokens in historical context; focus of token properties such as token type and token frequency. |
| Outcome: | The proposed method achieves state-of-the-art performance across all evaluation metrics and eliminates the need for additional information. |
Reference-free Hallucination Detection for Large Vision-Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large vision-language models exhibit excellent ability in language understanding, question answering, and conversations of visual inputs, but they are prone to producing hallucinations. |
| Approach: | They propose to use supervised uncertainty quantification methods to detect hallucinations in large vision-language models. |
| Outcome: | The proposed methods outperform the others in detecting hallucinations on four representative LVLMs across two different tasks. |
Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection for text-based LLMs do not capture audio-specific signals. |
| Approach: | They propose to capture pathological attention patterns associated with hallucination using four attention-derived metrics to train lightweight logistic regression classifiers. |
| Outcome: | The proposed approach outperforms baselines on in-domain data and generalises to out-of-domain ASR settings. |
Hallucination Detection in LLMs with Topological Divergence on Attention Graphs (2026.acl-long)
Copied to clipboard
Alexandra Bazarova, Andrei Volodichev, Aleksandr Yugay, Andrey Shulga, Alina Ermilova, Konstantin Polev, Julia Belikova, Rauf Parchiev, Dmitry Simakov, Maxim Savchenko, Andrey Savchenko, Serguei Barannikov, Alexey Zaytsev
| Challenge: | Large language models (LLMs) are prone to producing so-called hallucinations, i.e., content that is factually or contextually incorrect. |
| Approach: | They propose a TOpology-based HAllucination detector which quantifies the structural properties of graphs induced by attention matrices. |
| Outcome: | The proposed detector achieves state-of-the-art or competitive results on several benchmarks while requiring minimal annotated data and computational resources. |
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection (2023.tacl-1)
Copied to clipboard
| Challenge: | Neural sequence generation models produce outputs that are unrelated to the source text, and are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. |
| Approach: | They first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinous vs. non-hallucinated outputs generated via source perturbations. |
| Outcome: | The proposed detector outperforms both baseline models and strong classifiers on English-Chinese and German-English translation test beds. |
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence (2025.acl-long)
Copied to clipboard
Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua, Jinqiao Wang
| Challenge: | Existing methods focus on alignment training or decoding refinements but address symptoms at the generation stage without probing the underlying causes. |
| Approach: | They propose a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads. |
| Outcome: | The proposed method achieves superior performance compared to state-of-the-art approaches in mitigating hallucinations while maintaining high efficiency with negligible additional time overhead. |
Principled Detection of Hallucinations in Large Language Models via Multiple Testing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to detect hallucinations are prone to generating false alarms and false feedbacks. |
| Approach: | They propose a method that aggregates multiple evaluation scores via conformal p-values, enabling calibrated detection with controlled false alarm rate. |
| Outcome: | The proposed method aggregates multiple evaluation scores via conformal p-values, enabling calibrated detection with controlled false alarm rate. |
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to detect hallucinations depend on model internal states to estimate uncertainty, but they focus on last or mean tokens. |
| Approach: | They propose a supervised hallucination detection framework that leverages token-wise, layer-wise features derived from hidden states. |
| Outcome: | The proposed framework outperforms baseline models and avoids large training sets. |