Challenge: Concept-based explanations quantify how high-level concepts influence model behavior . existing benchmarks rely on costly human-written counterfactuals that serves as imperfect proxy .
Approach: They propose a framework for constructing datasets containing structural counterfactual pairs . they use a structured Causal Model to generate a concept-based explanation .
Outcome: The proposed framework compares concept-based explanations to causal effects estimated from counterfactuals.

Similar Papers

Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for evaluating concepts from different perspectives lack a unified formalization.
Approach: They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks.
Outcome: Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures.
A Causal Lens for Evaluating Faithfulness Metrics (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability, but they may not reflect the model’s truereasoning faithfully.
Approach: They propose a testbed framework for evaluating faithfulness metrics for natural language explanations using diagnosticity and model-editing methods.
Outcome: The proposed framework evaluates faithfulness metrics for natural language explanations on four tasks including fact-checking, analogy, object counting, and multi-hop reasoning.
Bridging Internal Consistency and External Alignment: A Causal and Dynamic Interpretability Framework for LLM Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing interpretability methods focus on internal and external aspects of the model . existing explanations often focus on surface correlations or static dependencies .
Approach: They propose a causal and dynamic interpretability framework for Large Language Models . they characterize backdoor-adjusted causal effects of generated prefix and prompt .
Outcome: The proposed framework provides a unified causal view of internal consistency and external alignment in LLM generation dynamics.
Faithful Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance (2026.acl-long)

Copied to clipboard

Challenge: Prior work has focused on generating convincing rationales that appear to be subjectively faithful, but it remains unclear whether these explanations are epistemic faithful.
Approach: They propose a method that enhances epistemic faithfulness by guiding explanation generation through attention-level interventions, informed by token-level heatmaps.
Outcome: The proposed method significantly improves epistemic faithfulness across multiple models, benchmarks, and prompts.
Language Models as Causal Effect Generators (2025.emnlp-main)

Copied to clipboard

Challenge: Using sequence-driven structural causal models (SD-SCMs) we characterize how SD-SCAMs enables sampling from observational, interventional, and counterfactual distributions according to the desired causal structure.
Approach: They propose a sequence-driven structural causal model that uses language models to parameterize a structural causal system based on a user-specified DAG.
Outcome: The proposed method outperforms state-of-the-art methods and can underpin auditing of language models for (un)desirable causal effects, such as misinformation or discrimination.
Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence (2026.findings-acl)

Copied to clipboard

Challenge: Existing models are overwhelmingly accurate when presented with counterfactual medical evidence . prior work explored conflicts between context and LLM parametric knowledge in the general domain .
Approach: They construct a counterfactual medical QA dataset that requires models to answer clinical comparison questions with evidence from randomized controlled trials.
Outcome: The proposed model overemphasizes the latter, and the model overestimates the latter.
Explaining Language Model Predictions with High-Impact Concepts (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods to explain large language models (LLMs) are mostly correlational and lack causal features due to compositional nature of languages.
Approach: They propose a framework to provide impact-aware explanations for large language models that are robust to feature changes and influential to the model’s predictions.
Outcome: The proposed explanations improve on real and synthetic tasks and are robust to feature changes and influential to the model’s predictions.
Can LLMs Explain Themselves Counterfactually? (2025.emnlp-main)

Copied to clipboard

Challenge: Explanations are an important tool for gaining insights into model behavior, calibrating user trust, and ensuring compliance.
Approach: They propose to use self-explanation to prompt models to explain outputs . they find that LLMs struggle to generate SCEs - their prediction often does not agree with their own counterfactual reasoning.
Outcome: The proposed methods can generate SCEs across families, sizes, temperatures, and datasets.
ConSim: Measuring Concept-Based Explanations’ Effectiveness with Automated Simulatability (2025.acl-long)

Copied to clipboard

Challenge: Existing evaluation metrics focus only on the quality of the induced space of possible concepts, neglecting the latter.
Approach: They propose to use large language models as simulators to approximate the evaluation and report various analyses to make such approximations reliable.
Outcome: The proposed framework allows for scalable and consistent evaluation across models and datasets.
MDC-Bench: A Multidisciplinary Causal Benchmark Based on Causal Structures for Evaluating Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing causal datasets focus on the commonsense domain, but LLMs perform poorly when answering complex questions.
Approach: They propose a multidisciplinary causal evaluation benchmark to assess LLMs' knowledge and skills.
Outcome: The proposed model improves in domain specialization, structural diversity, and task complexity.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations