LLM Explainability with Counterfactual Chains and Causal Graphs

• URL: http://arxiv.org/abs/2606.05972v1
• Date: Thu, 04 Jun 2026 10:15:12 GMT
• Title: LLM Explainability with Counterfactual Chains and Causal Graphs
• Abstract summary: Causal graphs provide a high-level language for making mechanisms transparent.<n>Recent work uses Large Language Models (LLMs) to recover causal graphs of external-world processes.<n>We use causal graphs to model LLM inference itself, providing stakeholders with a transparent view of how the model perceives and organizes high-level concepts to produce a prediction.
• Score: 19.857433252352482
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Causal graphs provide a high-level language for making mechanisms transparent. Recent work uses Large Language Models (LLMs) to recover causal graphs of external-world processes. Instead, in this paper, we use causal graphs to model LLM inference itself, providing stakeholders with a transparent view of how the model perceives and organizes high-level concepts to produce a prediction. We propose a four-phase method for constructing such graphs. Given a target LLM and a set of textual examples, our method discovers class-discriminative, human-interpretable concepts and maps each input to LLM-perceived concept states. We then introduce an MCMC-inspired counterfactual augmentation procedure that expands the sparse observational data through chains of counterfactuals. This enables stable causal discovery with $σ$-CG, yielding informative, interpretable graphs. We apply our method to three LLMs across disease diagnosis, sentiment analysis, and LLM-as-a-judge classification tasks. We evaluate the learned graphs for predictive fidelity and structural stability, and the MCMC-inspired augmentation for convergence and downstream utility. Our results show that the discovered causal graphs capture meaningful dependencies consistent with LLMs' reasoning. Together, this paper provides a foundation for concept-level explainability of LLMs.

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)
• KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning? [4.473915603131591]
  Chain-of-thought traces have been shown to improve performance of large language models in a plethora of reasoning tasks.<n>We introduce Causal CoT Graphs (CCGs), which are directed acyclic graphs automatically extracted from reasoning traces.
  arXiv  Detail & Related papers  (2025-07-15T15:28:37Z)
• Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM [11.181783720439563]
  Large Language Models (LLMs) display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation.<n>RLMs often demonstrate counterintuitive and unstable behaviors, such as performance degradation under few-shot prompting.<n>We introduce a unified graph-based analytical framework for better modeling the reasoning processes of RLMs.
  arXiv  Detail & Related papers  (2025-05-20T03:54:57Z)
• What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs [69.48708136448694]
  Large language models (LLMs) are reorganizing in the AI community for their expected reasoning and inference abilities.<n>We believe this kind of parametric representation of graphs, graph laws, can be a solution for making LLMs understand graph data as the input.
  arXiv  Detail & Related papers  (2024-10-16T00:01:31Z)
• How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension [53.6373473053431]
  This work introduces a benchmark to assess large language models' capabilities in graph pattern tasks.<n>We have developed a benchmark that evaluates whether LLMs can understand graph patterns based on either terminological or topological descriptions.<n>Our benchmark encompasses both synthetic and real datasets, and a variety of models, with a total of 11 tasks and 7 models.
  arXiv  Detail & Related papers  (2024-10-04T04:48:33Z)
• Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path [53.71787069694794]
  We focus on the graph reasoning ability of Large Language Models (LLMs)<n>We revisit the ability of LLMs on three fundamental graph tasks: graph description translation, graph connectivity, and the shortest-path problem.<n>Our findings suggest that LLMs can fail to understand graph structures through text descriptions and exhibit varying performance for all these fundamental tasks.
  arXiv  Detail & Related papers  (2024-08-18T16:26:39Z)
• Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness [39.57155321515097]
  Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing tasks. It remains unclear whether LLMs exhibit robustness in learning on graphs.
  arXiv  Detail & Related papers  (2024-07-16T09:05:31Z)
• Can LLM Graph Reasoning Generalize beyond Pattern Memorization? [46.93972334344908]
  We evaluate whether large language models (LLMs) can go beyond semantic, numeric, structural, reasoning patterns in the synthetic training data and improve utility on real-world graph-based tasks. We find that while post-training alignment is most promising for real-world tasks, empowering LLM graph reasoning to go beyond pattern remains an open research question.
  arXiv  Detail & Related papers  (2024-06-23T02:59:15Z)
• Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? [55.5662721046769]
  Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction.<n>Previous studies have explored LLMs' graph reasoning abilities through various techniques.<n>A critical factor has been mostly overlooked: the prompt sequential order in which graph descriptions are presented to the models.
  arXiv  Detail & Related papers  (2024-02-11T09:46:24Z)

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.