Copertina

Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yeo, Wei Jie, Satapathy, Ranjan, Cambria, Erik
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Interpretable are Reasoning Explanations from Prompting Large Language Models?
di: Yeo, Wei Jie, et al.
Pubblicazione: (2024)

Self-training Large Language Models through Knowledge Detection
di: Yeo, Wei Jie, et al.
Pubblicazione: (2024)

Plausible Extractive Rationalization through Semi-Supervised Entailment Signal
di: Yeo, Wei Jie, et al.
Pubblicazione: (2024)

Mitigating Jailbreaks with Intent-Aware LLMs
di: Yeo, Wei Jie, et al.
Pubblicazione: (2025)

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
di: Prakash, Nirmalendu, et al.
Pubblicazione: (2025)

Understanding Refusal in Language Models with Sparse Autoencoders
di: Yeo, Wei Jie, et al.
Pubblicazione: (2025)

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
di: Yeo, Wei Jie, et al.
Pubblicazione: (2025)

Explainable Natural Language Processing for Corporate Sustainability Analysis
di: Ong, Keane, et al.
Pubblicazione: (2024)

FaithLM: Towards Faithful Explanations for Large Language Models
di: Chuang, Yu-Neng, et al.
Pubblicazione: (2024)

A Systematic Analysis of Biases in Large Language Models
di: Zhang, Xulang, et al.
Pubblicazione: (2025)

Self-Critique and Refinement for Faithful Natural Language Explanations
di: Wang, Yingming, et al.
Pubblicazione: (2025)

Beyond Correlation: Refutation-Validated Aspect-Based Sentiment Analysis for Explainable Energy Market Returns
di: van der Heever, Wihan, et al.
Pubblicazione: (2026)

FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis
di: Ong, Keane, et al.
Pubblicazione: (2023)

Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models
di: Doi, Tomoki, et al.
Pubblicazione: (2025)

Natural Language Counterfactual Explanations for Graphs Using Large Language Models
di: Giorgi, Flavio, et al.
Pubblicazione: (2024)

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models
di: Agarwal, Chirag, et al.
Pubblicazione: (2024)

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
di: Yang, Zonglin, et al.
Pubblicazione: (2023)

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
di: Matton, Katie, et al.
Pubblicazione: (2025)

Large Language Models for Few-Shot Named Entity Recognition
di: Zhao, Yufei, et al.
Pubblicazione: (2018)

XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
di: Cambria, Erik, et al.
Pubblicazione: (2024)

ESGSenticNet: A Neurosymbolic Knowledge Base for Corporate Sustainability Analysis
di: Ong, Keane, et al.
Pubblicazione: (2025)

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
di: Wojciechowski, Adam, et al.
Pubblicazione: (2024)

The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
di: Siegel, Noah Y., et al.
Pubblicazione: (2024)

Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models
di: Gong, Xilin, et al.
Pubblicazione: (2026)

Logical Reasoning over Natural Language as Knowledge Representation: A Survey
di: Yang, Zonglin, et al.
Pubblicazione: (2023)

Towards Faithful Model Explanation in NLP: A Survey
di: Lyu, Qing, et al.
Pubblicazione: (2022)

CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation
di: Bandyopadhyay, Dibyanayan, et al.
Pubblicazione: (2025)

Situated Natural Language Explanations
di: Zhu, Zining, et al.
Pubblicazione: (2023)

Harnessing Large Language Models for Scientific Novelty Detection
di: Liu, Yan, et al.
Pubblicazione: (2025)

Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?
di: McMillan, Teague, et al.
Pubblicazione: (2025)

LExT: Towards Evaluating Trustworthiness of Natural Language Explanations
di: Shailya, Krithi, et al.
Pubblicazione: (2025)

On Measuring Faithfulness or Self-consistency of Natural Language Explanations
di: Parcalabescu, Letitia, et al.
Pubblicazione: (2023)

Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond
di: Xu, Fangzhi, et al.
Pubblicazione: (2023)

Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models
di: Sovrano, Francesco, et al.
Pubblicazione: (2026)

A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics
di: He, Kai, et al.
Pubblicazione: (2023)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
di: Anand, Nikhil, et al.
Pubblicazione: (2026)

From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models
di: Xu, Zexing, et al.
Pubblicazione: (2024)

Using Natural Language Explanations to Rescale Human Judgments
di: Wadhwa, Manya, et al.
Pubblicazione: (2023)

Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering
di: Li, Yangyi, et al.
Pubblicazione: (2025)

CELL your Model: Contrastive Explanations for Large Language Models
di: Luss, Ronny, et al.
Pubblicazione: (2024)