# Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach

arXiv: https://arxiv.org/abs/2501.11041 · HTML: https://mlsanity.com/paper/2501.11041/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 19 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study](https://mlsanity.com/paper/2304.04339/) (2023)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Prompt Consistency for Zero-Shot Task Generalization](https://mlsanity.com/paper/2205.00049/) (2022)
- [Measuring Reliability of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2211.05853/) (2022)
- [Predicting Question-Answering Performance of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2311.01152/) (2023)

## Built on by (most cited first, 14 of 14)

- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [StaRPO: Stability-Augmented Reinforcement Policy Optimization](https://mlsanity.com/paper/2604.08905/) (2026)
- [ConMeC: A Dataset for Metonymy Resolution with Common Nouns](https://mlsanity.com/paper/2502.06087/) (2025)
- [Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding](https://mlsanity.com/paper/2504.00409/) (2025)
- [CAPE: Context-Aware Personality Evaluation Framework for Large Language Models](https://mlsanity.com/paper/2508.20385/) (2025)
- [Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs](https://mlsanity.com/paper/2510.14242/) (2025)
- [Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs](https://mlsanity.com/paper/2601.14311/) (2026)
- [Probing the Lack of Stable Internal Beliefs in LLMs](https://mlsanity.com/paper/2603.25187/) (2026)
- [Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning](https://mlsanity.com/paper/2604.05756/) (2026)
- [LLM Explainability with Counterfactual Chains and Causal Graphs](https://mlsanity.com/paper/2606.05972/) (2026)
- [Automated Creativity Evaluation of Language Models Across Open-Ended Tasks](https://mlsanity.com/paper/2606.11762/) (2026)
- [Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment](https://mlsanity.com/paper/2510.03520/) (2025)
- [Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier](https://mlsanity.com/paper/2512.01514/) (2025)

## Abstract (arXiv)

A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve semantic consistency of an LLM, one of the key approaches is to finetune the model with prompt-output pairs with semantically equivalent meanings. Despite its effectiveness, a data-driven finetuning method incurs substantial computation costs in data preparation and model optimization. In this regime, an LLM is treated as a ``black box'', restricting our ability to gain deeper insights into its internal mechanism. In this paper, we are motivated to enhance the semantic consistency of LLMs through a more interpretable method (i.e., model editing) to this end. We first identify the model components (i.e., attention heads) that have a key impact on the semantic consistency of an LLM. We subsequently inject biases into the output of these model components along the semantic-consistency activation direction. It is noteworthy that these modifications are cost-effective, without reliance on mass manipulations of the original model parameters. Through comprehensive experiments on the constructed NLU and open-source NLG datasets, our method demonstrates significant improvements in the semantic consistency and task performance of LLMs. Additionally, our method exhibits promising generalization capabilities by performing well on tasks beyond the primary tasks.