# In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

arXiv: https://arxiv.org/abs/2403.01548 · HTML: https://mlsanity.com/paper/2403.01548/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 3 Mar 2024.

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Analyzing Transformers in Embedding Space](https://mlsanity.com/paper/2209.02535/) (2022)
- [Improving Language Models via Plug-and-Play Retrieval Feedback](https://mlsanity.com/paper/2305.14002/) (2023)
- [Overthinking the Truth: Understanding how Language Models Process False Demonstrations](https://mlsanity.com/paper/2307.09476/) (2023)
- [Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models](https://mlsanity.com/paper/2309.15098/) (2023)
- [FELM: Benchmarking Factuality Evaluation of Large Language Models](https://mlsanity.com/paper/2310.00741/) (2023)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)

## Built on by (most cited first, 30 of 45)

- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas](https://mlsanity.com/paper/2503.01773/) (2025)
- [MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation](https://mlsanity.com/paper/2410.11779/) (2024)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models](https://mlsanity.com/paper/2410.03577/) (2024)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations](https://mlsanity.com/paper/2410.18860/) (2024)
- [A Survey on the Honesty of Large Language Models](https://mlsanity.com/paper/2409.18786/) (2024)
- [Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation](https://mlsanity.com/paper/2506.17088/) (2025)
- [SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence](https://mlsanity.com/paper/2502.08767/) (2025)
- [Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval](https://mlsanity.com/paper/2405.06545/) (2024)
- [SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models](https://mlsanity.com/paper/2411.02433/) (2024)
- [Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs](https://mlsanity.com/paper/2510.01218/) (2025)
- [VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding](https://mlsanity.com/paper/2411.15839/) (2024)
- [Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation](https://mlsanity.com/paper/2505.23657/) (2025)
- [Integrative Decoding: Improve Factuality via Implicit Self-consistency](https://mlsanity.com/paper/2410.01556/) (2024)
- [Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models](https://mlsanity.com/paper/2502.03199/) (2025)
- [Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics](https://mlsanity.com/paper/2504.00446/) (2025)
- [SED: Self-Evaluation Decoding Enhances Large Language Models for Better Generation](https://mlsanity.com/paper/2405.16552/) (2024)
- [Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2505.19498/) (2025)
- [Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs](https://mlsanity.com/paper/2510.00705/) (2025)
- [DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models](https://mlsanity.com/paper/2503.03149/) (2025)
- [Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation](https://mlsanity.com/paper/2503.08963/) (2025)
- [LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers](https://mlsanity.com/paper/2507.04404/) (2025)
- [PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality](https://mlsanity.com/paper/2509.16598/) (2025)
- [What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis](https://mlsanity.com/paper/2502.13490/) (2025)
- [TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction](https://mlsanity.com/paper/2503.04457/) (2025)

## Abstract (arXiv)

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based metric to quantify the ``sharpness'' among the in-context hidden states and incorporate it into the decoding process to formulate a constrained decoding approach. Experiments on various knowledge-seeking and hallucination benchmarks demonstrate our approach's consistent effectiveness, for example, achieving up to an 8.6 point improvement on TruthfulQA. We believe this study can improve our understanding of hallucinations and serve as a practical solution for hallucination mitigation.