Imagen de Portada

Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Doi, Tomoki, Isonuma, Masaru, Yanaka, Hitomi
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Comprehensive Evaluation of Large Language Models for Topic Modeling
por: Doi, Tomoki, et al.
Publicado: (2024)

Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?
por: Shinozaki, Taiga, et al.
Publicado: (2025)

Unlearning Traces the Influential Training Data of Language Models
por: Isonuma, Masaru, et al.
Publicado: (2024)

Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models
por: Kumon, Ryoma, et al.
Publicado: (2026)

Can Large Language Models Robustly Perform Natural Language Inference for Japanese Comparatives?
por: Mikami, Yosuke, et al.
Publicado: (2025)

What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?
por: Ryu, Koki, et al.
Publicado: (2026)

Bridging Perception and Language: A Systematic Benchmark for LVLMs' Understanding of Amodal Completion Reports
por: Watahiki, Amane, et al.
Publicado: (2025)

Analyzing the Inner Workings of Transformers in Compositional Generalization
por: Kumon, Ryoma, et al.
Publicado: (2025)

Neuron-Level Analysis of Cultural Understanding in Large Language Models
por: Yamamoto, Taisei, et al.
Publicado: (2025)

What's New in My Data? Novelty Exploration via Contrastive Generation
por: Isonuma, Masaru, et al.
Publicado: (2024)

UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
por: Lu, Huimin, et al.
Publicado: (2025)

Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
por: Ryu, Koki, et al.
Publicado: (2025)

NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension
por: Li, Rongzhi, et al.
Publicado: (2026)

Evaluating Structural Generalization in Neural Machine Translation
por: Kumon, Ryoma, et al.
Publicado: (2024)

Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models
por: Someya, Taiga, et al.
Publicado: (2025)

Instability in Downstream Task Performance During LLM Pretraining
por: Nishida, Yuto, et al.
Publicado: (2025)

Developing a Guideline for the Labovian-Structural Analysis of Oral Narratives in Japanese
por: Watahiki, Amane, et al.
Publicado: (2026)

LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese
por: Lu, Jie, et al.
Publicado: (2025)

Implementing a Logical Inference System for Japanese Comparatives
por: Mikami, Yosuke, et al.
Publicado: (2025)

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
por: Kojima, Takeshi, et al.
Publicado: (2024)

Exploring Intra and Inter-language Consistency in Embeddings with ICA
por: Li, Rongzhi, et al.
Publicado: (2024)

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

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

J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling
por: Nakata, Wataru, et al.
Publicado: (2024)

JBBQ: Japanese Bias Benchmark for Analyzing Social Biases in Large Language Models
por: Yanaka, Hitomi, et al.
Publicado: (2024)

Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset
por: Yamamoto, Taisei, et al.
Publicado: (2025)

Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation
por: Lu, Huimin, et al.
Publicado: (2024)

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

Exclusive Unlearning
por: Sasaki, Mutsumi, et al.
Publicado: (2026)

Towards Automated Lexicography: Generating and Evaluating Definitions for Learner's Dictionaries
por: Ide, Yusuke, et al.
Publicado: (2026)

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

DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models
por: Guo, YiQiu, et al.
Publicado: (2025)

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

Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training
por: Li, Dongfang, et al.
Publicado: (2023)

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective
por: Yanaka, Hitomi, et al.
Publicado: (2025)

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

Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
por: Yeo, Wei Jie, et al.
Publicado: (2024)

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment
por: Bhan, Milan, et al.
Publicado: (2025)

Large Language Model Agents Are Not Always Faithful Self-Evolvers
por: Zhao, Weixiang, et al.
Publicado: (2026)

Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
por: Fragkathoulas, Christos, et al.
Publicado: (2024)