Copertina

ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Poché, Antonin, Jacovi, Alon, Picard, Agustin Martin, Boutin, Victor, Jourdan, Fanny
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
di: Bernas, Raphael, et al.
Pubblicazione: (2026)

TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes
di: Jourdan, Fanny, et al.
Pubblicazione: (2023)

Counterfactual Simulatability of LLM Explanations for Generation Tasks
di: Limpijankit, Marvin, et al.
Pubblicazione: (2025)

Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability
di: Jourdan, Fanny
Pubblicazione: (2024)

Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning
di: Fouilhé, Guilhem, et al.
Pubblicazione: (2026)

Interpreto: An Explainability Library for Transformers
di: Poché, Antonin, et al.
Pubblicazione: (2025)

Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations
di: Hong, Pingjun, et al.
Pubblicazione: (2026)

FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity
di: Jourdan, Fanny, et al.
Pubblicazione: (2025)

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP
di: Goldman, Omer, et al.
Pubblicazione: (2024)

ALMANACS: A Simulatability Benchmark for Language Model Explainability
di: Mills, Edmund, et al.
Pubblicazione: (2023)

Magnetism of stable structures of small binary ConSim (n + m < 4) clusters
di: E.M Sosa-Hernández
Pubblicazione: (2008)

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
di: Dhimoïla, Grégoire, et al.
Pubblicazione: (2026)

TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
di: Caciularu, Avi, et al.
Pubblicazione: (2024)

A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains
di: Jacovi, Alon, et al.
Pubblicazione: (2024)

CoverBench: A Challenging Benchmark for Complex Claim Verification
di: Jacovi, Alon, et al.
Pubblicazione: (2024)

Bisimilarity and Simulatability of Processes Parameterized by Join Interactions
di: Grabmayer, Clemens, et al.
Pubblicazione: (2025)

ConQuer: A Framework for Concept-Based Quiz Generation
di: Fu, Yicheng, et al.
Pubblicazione: (2025)

Latent Concept-based Explanation of NLP Models
di: Yu, Xuemin, et al.
Pubblicazione: (2024)

Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
di: Alon, Bar, et al.
Pubblicazione: (2026)

ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation
di: Dong, Weilong, et al.
Pubblicazione: (2024)

ConExion: Concept Extraction with Large Language Models
di: Norouzi, Ebrahim, et al.
Pubblicazione: (2025)

DoubleDipper: Improving Long-Context LLMs via Context Recycling
di: Cattan, Arie, et al.
Pubblicazione: (2024)

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery
di: Sun, Yifan, et al.
Pubblicazione: (2025)

Explanation sensitivity to the randomness of large language models: the case of journalistic text classification
di: Bogaert, Jeremie, et al.
Pubblicazione: (2024)

DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
di: Cattan, Arie, et al.
Pubblicazione: (2025)

ConStat: Performance-Based Contamination Detection in Large Language Models
di: Dekoninck, Jasper, et al.
Pubblicazione: (2024)

FGR-ColBERT: Identifying Fine-Grained Relevance Tokens During Retrieval
di: Jarolím, Antonín, et al.
Pubblicazione: (2026)

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
di: Toker, Gilat, et al.
Pubblicazione: (2026)

Can LLMs extract human-like fine-grained evidence for evidence-based fact-checking?
di: Jarolím, Antonín, et al.
Pubblicazione: (2025)

A Straightforward Pipeline for Targeted Entailment and Contradiction Detection
di: Sulc, Antonin
Pubblicazione: (2025)

Towards a Framework for Evaluating Explanations in Automated Fact Verification
di: Kotonya, Neema, et al.
Pubblicazione: (2024)

Zonkey: A Hierarchical Diffusion Language Model with Differentiable Tokenization and Probabilistic Attention
di: Rozental, Alon
Pubblicazione: (2026)

Estimation of Concept Explanations Should be Uncertainty Aware
di: Piratla, Vihari, et al.
Pubblicazione: (2023)

Event2Vec: A Geometric Approach to Learning Composable Representations of Event Sequences
di: Sulc, Antonin
Pubblicazione: (2025)

Effective Explanations Support Planning Under Uncertainty
di: Zhou, Hanqi, et al.
Pubblicazione: (2026)

AutoPCR: Automated Phenotype Concept Recognition by Prompting
di: Tao, Yicheng, et al.
Pubblicazione: (2025)

Automate Knowledge Concept Tagging on Math Questions with LLMs
di: Li, Hang, et al.
Pubblicazione: (2024)

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
di: Pala, Tej Deep, et al.
Pubblicazione: (2024)

LLM-Augmented Changepoint Detection: A Framework for Ensemble Detection and Automated Explanation
di: Lukassen, Fabian, et al.
Pubblicazione: (2026)

Examining the Metrics for Document-Level Claim Extraction in Czech and Slovak
di: Makaiova, Lucia, et al.
Pubblicazione: (2025)