Challenge: Large Language Models (LLMs) have demonstrated remarkable performance across tasks but remain prone to hallucinations.
Approach: They propose a method that uses attention maps to detect hallucinations . they propose to use top-k eigenvalues of the attention maps as input to probes .
Outcome: The proposed method achieves state-of-the-art hallucination detection performance among attention-based methods.

Similar Papers

Hallucination Detection in LLMs with Topological Divergence on Attention Graphs (2026.acl-long)

Copied to clipboard

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.
InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for detecting hallucinations in large language models are limited due to their high frequency and high accuracy.
Approach: They propose a method to detect hallucinations in large language models by repeating model-generated responses from its generated answer.
Outcome: The proposed method achieves 87% hallucinations in a specific experiment without external knowledge.
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.
HalluZig: Hallucination Detection using Zigzag Persistence (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for hallucination detection rely on surface-level signals from the model output, overlooking the failures within the model’s internal reasoning process.
Approach: They propose a framework that analyzes the dynamic topology of the evolution of model’s layer-wise attention and leverage zigzag persistence to extract a topological signature.
Outcome: The proposed framework outperforms baselines on multiple benchmarks and is generalizable across models.
Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Hallucination is a significant barrier to the effective application of Large Language Models (LLMs).
Approach: They propose an Attention-Guided SElf-Reflection approach for hallucination detection in Large Language Models.
Outcome: The proposed method significantly outperforms existing methods in zero-shot hallucination detection on four widely-used LLMs across three different halluciation benchmarks.
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies have recognized hallucination as a notable concern in large autoregressive language models (LLMs).
Approach: They propose a polygraph for large language models that detects "hallucination" they demonstrate that hallucination can be detected by tractable probabilistic models .
Outcome: The proposed model outperforms state-of-the-art methods on open-source LLMs by 20% on TruthfulQA benchmarks.
The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models have generated widespread acclaim, but hallucination has also emerged as a by-product.
Approach: They propose a fine-grained discourse on profiling hallucination based on its degree, orientation, and category . they categorize hallucines into six types: acronym ambiguity, generated golem, virtual voice, geographic erratum, time wrap .
Outcome: The proposed method categorizes hallucination into six types based on their degree, orientation, and category .
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.
VADE: Visual Attention Guided Hallucination Detection and Elimination (2025.findings-acl)

Copied to clipboard

Challenge: Vision Language Models (VLMs) are prone to hallucinations, generating outputs that lack grounding in the actual visual data.
Approach: They propose a sequence modelling approach to learn complex sequential patterns from transformer attention maps.
Outcome: The proposed approach achieves an average PR-AUC of 80% in hallucination detection on M-HalDetect and an 5% improvement in hallucinosis mitigation on MSCOCO.
Tutorial Proposal: Hallucination in Large Language Models (2024.lrec-tutorials)

Copied to clipboard

Challenge: Grasping the intricacies of hallucination in LLMs can be daunting, especially for those new to the field.
Approach: This tutorial aims to bridge the gap between the field and the field of hallucination . it will explore the key aspects of hallucinonation, including benchmarking, detection, and mitigation techniques .
Outcome: This tutorial will explore the key aspects of hallucination in LLMs . it will also explore the specific constraints and shortcomings of current approaches .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations