# Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework

arXiv: https://arxiv.org/abs/2509.21241 · HTML: https://mlsanity.com/paper/2509.21241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [Local Rule-Based Explanations of Black Box Decision Systems](https://mlsanity.com/paper/1805.10820/) (2018)
- [SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales](https://mlsanity.com/paper/2405.20974/) (2024)
- [Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey](https://mlsanity.com/paper/2311.07914/) (2023)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks](https://mlsanity.com/paper/2403.03792/) (2024)
- [Domain-specific Knowledge Graphs: A survey](https://mlsanity.com/paper/2011.00235/) (2020)
- [Sequential Integrated Gradients: a simple but effective method for explaining language models](https://mlsanity.com/paper/2305.15853/) (2023)
- [FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles](https://mlsanity.com/paper/1911.12199/) (2019)
- [Concept Bottleneck Large Language Models](https://mlsanity.com/paper/2412.07992/) (2024)
- [TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2407.10114/) (2024)

## Abstract (arXiv)

The widespread adoption of Low-Rank Adaptation (LoRA) has enabled large language models (LLMs) to acquire domain-specific knowledge with remarkable efficiency. However, understanding how such a fine-tuning mechanism alters a model's structural reasoning and semantic behavior remains an open challenge. This work introduces a novel framework that explains fine-tuned LLMs via counterfactuals grounded in knowledge graphs. Specifically, we construct BioToolKG, a domain-specific heterogeneous knowledge graph in bioinformatics tools and design a counterfactual-based fine-tuned LLMs explainer (CFFTLLMExplainer) that learns soft masks over graph nodes and edges to generate minimal structural perturbations that induce maximum semantic divergence. Our method jointly optimizes structural sparsity and semantic divergence while enforcing interpretability preserving constraints such as entropy regularization and edge smoothness. We apply this framework to a fine-tuned LLaMA-based LLM and reveal that counterfactual masking exposes the model's structural dependencies and aligns with LoRA-induced parameter shifts. This work provides new insights into the internal mechanisms of fine-tuned LLMs and highlights counterfactual graphs as a potential tool for interpretable AI.