Image de couverture de livre

FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Nakyeong, Kim, Minsung, Yoon, Seunghyun, Shin, Joongbo, Jung, Kyomin
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
par: Yang, Nakyeong, et autres
Publié: (2023)

How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
par: Kim, Minsung, et autres
Publié: (2025)

Rethinking Post-Unlearning Behavior of Large Vision-Language Models
par: Kim, Minsung, et autres
Publié: (2025)

Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
par: Yang, Nakyeong, et autres
Publié: (2024)

Avoidance Decoding for Diverse Multi-Branch Story Generation
par: Park, Kyeongman, et autres
Publié: (2025)

LongStory: Coherent, Complete and Length Controlled Long story Generation
par: Park, Kyeongman, et autres
Publié: (2023)

VLind-Bench: Measuring Language Priors in Large Vision-Language Models
par: Lee, Kang-il, et autres
Publié: (2024)

Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
par: Yang, Nakyeong, et autres
Publié: (2023)

FaithLM: Towards Faithful Explanations for Large Language Models
par: Chuang, Yu-Neng, et autres
Publié: (2024)

FaithLens: Detecting and Explaining Faithfulness Hallucination
par: Si, Shuzheng, et autres
Publié: (2025)

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
par: Li, Yuepei, et autres
Publié: (2024)

Persona Switch: Mixing Distinct Perspectives in Decoding Time
par: Kim, Junseok, et autres
Publié: (2026)

Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
par: Kim, Junseok, et autres
Publié: (2024)

KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
par: Kim, Jinyoung, et autres
Publié: (2026)

Program Synthesis via Test-Time Transduction
par: Lee, Kang-il, et autres
Publié: (2025)

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

Dissociation of Faithful and Unfaithful Reasoning in LLMs
par: Yee, Evelyn, et autres
Publié: (2024)

Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
par: Yang, Chenxu, et autres
Publié: (2025)

SFR-RAG: Towards Contextually Faithful LLMs
par: Nguyen, Xuan-Phi, et autres
Publié: (2024)

Closing the Confidence-Faithfulness Gap in Large Language Models
par: Miao, Miranda Muqing, et autres
Publié: (2026)

Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering
par: Zhai, Weihe, et autres
Publié: (2023)

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
par: Sui, Yuan, et autres
Publié: (2024)

Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
par: Koh, Hyukhun, et autres
Publié: (2024)

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
par: Ju, Li, et autres
Publié: (2026)

TrueBrief: Faithful Summarization through Small Language Models
par: Lakara, Kumud, et autres
Publié: (2025)

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
par: Luo, Linhao, et autres
Publié: (2023)

Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
par: Xiong, Guangzhi, et autres
Publié: (2025)

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models
par: Lv, Weijiang, et autres
Publié: (2026)

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
par: Lv, Weijiang, et autres
Publié: (2026)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
par: Ming, Yifei, et autres
Publié: (2024)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
par: Cho, Seonglae, et autres
Publié: (2025)

Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
par: Zhao, Tianzhe, et autres
Publié: (2026)

Context-DPO: Aligning Language Models for Context-Faithfulness
par: Bi, Baolong, et autres
Publié: (2024)

Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
par: Ma, Shengjie, et autres
Publié: (2024)

Conditional [MASK] Discrete Diffusion Language Model
par: Koh, Hyukhun, et autres
Publié: (2024)

Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation
par: Sun, Zhouhao, et autres
Publié: (2024)

Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
par: Li, Jiachun, et autres
Publié: (2024)

Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
par: Alon, Bar, et autres
Publié: (2026)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
par: Mittal, Avni, et autres
Publié: (2026)

Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations
par: Jang, Yoonna, et autres
Publié: (2024)