Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework

• URL: http://arxiv.org/abs/2509.21241v1
• Date: Thu, 25 Sep 2025 14:37:40 GMT
• Title: Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
• Abstract summary: Low-Rank Adaptation (LoRA) has enabled large language models to acquire domain-specific knowledge with remarkable efficiency.<n>This work introduces a novel framework that explains fine-tuned LLMs via counterfactuals grounded in knowledge graphs.
• Score: 13.533352973355013
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SLASH the Sink: Sharpening Structural Attention Inside LLMs [55.75072688988806]
  Large Language Models (LLMs) show remarkable semantic understanding but struggle with structural understanding when processing graph topologies in a serialized format.<n>We propose StructuraL Attention SHarpening (SLASH), which amplifies this internal structural understanding via a plug-and-play attention redistribution.
  arXiv  Detail & Related papers  (2026-05-11T12:59:07Z)
• MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing [23.48465917752293]
  Large Language Models (LLMs) offer strong reasoning capabilities but struggle with limited context windows and hallucinations.<n>We propose MERIT (Memory-Enhanced Retrieval for Interpretable Knowledge Tracing), a training-free framework combining frozen LLM reasoning with structured pedagogical memory.<n>By grounding the LLM in interpretable memory, MERIT achieves state-of-the-art performance on real-world datasets without gradient updates.
  arXiv  Detail & Related papers  (2026-03-03T10:07:38Z)
• Matrix as Plan: Structured Logical Reasoning with Feedback-Driven Replanning [9.431480849387595]
  Chain-of-Thought prompting has been shown to enhance the reasoning capabilities of Large Language Models (LLMs)<n>Neuro-symbolic methods address this gap by enforcing formal correctness through external solvers.<n>We propose MatrixCoT, a structured CoT framework with a matrix-based plan.
  arXiv  Detail & Related papers  (2026-01-15T06:12:00Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction [51.83437071408662]
  We propose GLOW, a unified framework for AW performance prediction.<n>GLOW combines the graph-structure modeling capabilities of GNNs with the reasoning power of LLMs.<n>Experiments on FLORA-Bench show that GLOW outperforms state-of-the-art baselines in prediction accuracy and ranking utility.
  arXiv  Detail & Related papers  (2025-12-11T13:30:46Z)
• Towards Efficient LLM-aware Heterogeneous Graph Learning [47.42705995672551]
  We propose an Efficient LLM-Aware framework for heterogeneous graphs.<n>Our proposed ELLA outperforms state-of-the-art methods in the performance and efficiency.
  arXiv  Detail & Related papers  (2025-11-22T05:38:03Z)
• ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models [18.720486146234077]
  Large Language Models (LLMs) have emerged as a powerful paradigm for Knowledge Graph Completion (KGC)<n>We propose ReaLM, a novel and effective framework that bridges the gap between KG embeddings and LLM tokenization.<n>We show that ReaLM achieves state-of-the-art performance, confirming its effectiveness in aligning structured knowledge with large-scale language models.
  arXiv  Detail & Related papers  (2025-10-10T04:36:13Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge [88.82814893945077]
  Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge.<n>Recent graph-enhanced RAG (GraphRAG) attempts to bridge this gap by constructing tailored graphs and enabling LLMs to reason on them.<n>G-reasoner is a unified framework that integrates graph and language foundation models for reasoning over diverse graph-structured knowledge.
  arXiv  Detail & Related papers  (2025-09-29T04:38:12Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• Quantizing Text-attributed Graphs for Semantic-Structural Integration [6.721504414917793]
  Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains.<n>With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning.<n>We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using a frozen codebook.
  arXiv  Detail & Related papers  (2025-07-20T09:18:02Z)
• SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation [50.277959544420455]
  SAFT is a structure-aware fine-tuning approach that injects graph topology into pretrained language models.<n>We compute direction-sensitive positional encodings from the magnetic Laplacian of transformed AMRs.<n> SAFT sets a new state-of-the-art on AMR 3.0 with a 3.5 BLEU improvement over baselines.
  arXiv  Detail & Related papers  (2025-07-15T18:12:57Z)
• TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree [52.44403214958304]
  In this paper, we introduce TreeLoRA, a novel approach that constructs layer-wise adapters by leveraging hierarchical gradient similarity.<n>To reduce the computational burden of task similarity estimation, we employ bandit techniques to develop an algorithm based on lower confidence bounds.<n> experiments on both vision transformers (ViTs) and large language models (LLMs) demonstrate the effectiveness and efficiency of our approach.
  arXiv  Detail & Related papers  (2025-06-12T05:25:35Z)
• When can isotropy help adapt LLMs' next word prediction to numerical domains? [53.98633183204453]
  It is shown that the isotropic property of LLM embeddings in contextual embedding space preserves the underlying structure of representations.<n> Experiments show that different characteristics of numerical data and model architectures have different impacts on isotropy.
  arXiv  Detail & Related papers  (2025-05-22T05:10:34Z)
• Scalability Matters: Overcoming Challenges in InstructGLM with Similarity-Degree-Based Sampling [1.2805157669888096]
  We propose SDM-InstructGLM, a novel instruction-tuned Graph Language Model (InstructGLM) framework that enhances scalability and efficiency without relying on GNNs.<n>Our method introduces a similarity-degree-based biased random walk mechanism, which selectively samples and encodes graph information based on node-feature similarity and degree centrality.<n>Our results demonstrate the feasibility of LLM-only graph processing, enabling scalable and interpretable Graph Language Models (GLMs) optimized through instruction-based fine-tuning.
  arXiv  Detail & Related papers  (2025-05-02T06:08:21Z)
• Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation [9.844598565914055]
  Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge.<n>We introduce SubgraphRAG, extending the Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) framework that retrieves subgraphs.<n>Our approach innovatively integrates a lightweight multilayer perceptron with a parallel triple-scoring mechanism for efficient and flexible subgraph retrieval.
  arXiv  Detail & Related papers  (2024-10-28T04:39:32Z)
• Extending Token Computation for LLM Reasoning [5.801044612920816]
  Large Language Models (LLMs) are pivotal in advancing natural language processing. LLMs often struggle with complex reasoning tasks due to inefficient attention distributions. We introduce a novel method for extending computed tokens in the Chain-of-Thought process, utilizing attention mechanism optimization.
  arXiv  Detail & Related papers  (2024-03-22T03:23:58Z)
• CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model [22.870512676002463]
  This paper focuses on Offsite-Tuning (OFT), a representative technique that transfers transformer blocks between centralized LLMs and downstream emulators. Inspired by these observations, we propose CRaSh, involving Clustering, Removing, and Sharing, a training-free strategy to derive improved emulators from LLMs. Our findings demonstrate a linear connectivity among these optima falling over the same basin, thereby highlighting the effectiveness of CRaSh and OFT.
  arXiv  Detail & Related papers  (2023-10-24T03:08:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.