mlsanityData to 14 Oct 2026

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models

arXiv 2501.09997 ↗First posted 17 Jan 2025cs.CL cs.AIcited by 16

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

Hallucination has emerged as a significant barrier to the effective application of Large Language Models (LLMs). In this work, we introduce a novel Attention-Guided SElf-Reflection (AGSER) approach for zero-shot hallucination detection in LLMs. The AGSER method utilizes attention contributions to categorize the input query into attentive and non-attentive queries. Each query is then processed separately through the LLMs, allowing us to compute consistency scores between the generated responses and the original answer. The difference between the two consistency scores serves as a hallucination estimator. In addition to its efficacy in detecting hallucinations, AGSER notably reduces computational overhead, requiring only three passes through the LLM and utilizing two sets of tokens. We have conducted extensive experiments with four widely-used LLMs across three different hallucination benchmarks, demonstrating that our approach significantly outperforms existing methods in zero-shot hallucination detection.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 21 of its 39 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

21 of 39 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  7. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 688
  8. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  9. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 250
  10. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 244
  11. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  12. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 142
9 more
  1. 2024TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Spacecited by 91
  2. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 90
  3. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 80
  4. 2023Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Modelscited by 67
  5. 2024InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answerscited by 27
  6. 2024Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detectorcited by 20
  7. 2024Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decodingcited by 14
  8. 2024Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modelingcited by 9
  9. 2024Integrative Decoding: Improve Factuality via Implicit Self-consistencycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 7.

16 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 49
  3. 2025Robust Hallucination Detection in LLMs via Adaptive Token Selectioncited by 19
  4. 2025TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Modelscited by 8
  5. 2026TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphscited by 8
  6. 2025Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forwardcited by 6
  7. 2026HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoderscited by 5
  8. 2025Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Modelscited by 4
  9. 2025SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusioncited by 3
  10. 2026CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?cited by 2
  11. 2026Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agentscited by 1
  12. 2025AGIC: Attention-Guided Image Captioning to Improve Caption Relevancecited by 0
4 more
  1. 2025Thinking, Faithful and Stable: Mitigating Hallucinations in LLMscited by 0
  2. 2026Lowest Span Confidence: Zero-Shot Hallucination Detection from a Single LLM Responsecited by 0
  3. 2026Attention Sinks as Internal Signals for Hallucination Detection in Large Language Modelscited by 0
  4. 2026CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AggTruth: Contextual Hallucination Detection using Aggregated Attention Scores in LLMs
  2. 2025SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Models
  3. 2025(Im)possibility of Automated Hallucination Detection in Large Language Models
  4. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
  5. 2026Zero-source LLM Hallucination Detection with Human-like Criteria Probing
  6. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
  7. 2026Scalable Token-Level Hallucination Detection in Large Language Models
  8. 2024Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses