# Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models

arXiv: https://arxiv.org/abs/2602.00300 · HTML: https://mlsanity.com/paper/2602.00300/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 30 of 38)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Linearity of Relation Decoding in Transformer Language Models](https://mlsanity.com/paper/2308.09124/) (2023)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [RedPajama: an Open Dataset for Training Large Language Models](https://mlsanity.com/paper/2411.12372/) (2024)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing](https://mlsanity.com/paper/2410.06331/) (2024)
- [Understanding the Repeat Curse in Large Language Models from a Feature Perspective](https://mlsanity.com/paper/2504.14218/) (2025)
- [Dissecting Fine-Tuning Unlearning in Large Language Models](https://mlsanity.com/paper/2410.06606/) (2024)
- [RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns](https://mlsanity.com/paper/2508.13152/) (2025)
- [Exploring the Personality Traits of LLMs through Latent Features Steering](https://mlsanity.com/paper/2410.10863/) (2024)
- [When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs](https://mlsanity.com/paper/2511.02243/) (2025)
- [BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization](https://mlsanity.com/paper/2407.13928/) (2024)
- [Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models](https://mlsanity.com/paper/2508.10599/) (2025)

## Built on by (most cited first, 1 of 1)

- [Verbalizing Multi-Token Concepts in LLMs](https://mlsanity.com/paper/2608.31084/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong capabilities for hidden representation interpretation through Patchscopes, a framework that uses LLMs themselves to generate human-readable explanations by decoding from internal hidden representations. However, our work shows that LLMs tend to rely on inherent linguistic patterns, which can override contextual information encoded in the hidden representations during decoding. For example, even when a hidden representation encodes the contextual attribute "purple" for "broccoli", LLMs still generate "green" in their explanations, reflecting a strong prior association. This behavior reveals a systematic unfaithfulness in Patchscopes. To systematically study this issue, we first designed a dataset to evaluate the faithfulness of Patchscopes under biased cases, and our results show that there is an 18.84% faithfulness decrease on average. We then propose Bias Alignment through Logit Recalibration (BALOR), which treats the output logits from an unpatched prompt as capturing model bias and contrasts them with logits obtained under patched contextual information. By recalibrating the logit distribution through this contrast, BALOR suppresses model bias and amplifies contextual information during generation. Experiments across multiple LLMs demonstrate that BALOR consistently outperforms existing baselines, achieving up to 33% relative performance improvement.