Copertina

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Jiayu, Fan, Yuxuan, Lai, Songning, Wu, Shengen, Tang, Jiaqi, Kang, Chun, Guo, Zhijiang, Yue, Yutao
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

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
di: Zhang, Zhuoran, et al.
Pubblicazione: (2024)

Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains
di: Wu, Jiemin, et al.
Pubblicazione: (2024)

Multi-hop Question Answering under Temporal Knowledge Editing
di: Cheng, Keyuan, et al.
Pubblicazione: (2024)

Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall
di: Yuan, Jiaqing, et al.
Pubblicazione: (2024)

Geometric Factual Recall in Transformers
di: Ravfogel, Shauli, et al.
Pubblicazione: (2026)

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
di: Zhang, Mengqi, et al.
Pubblicazione: (2024)

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
di: Liu, Xiyu, et al.
Pubblicazione: (2024)

Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
di: Wang, Qianli, et al.
Pubblicazione: (2025)

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
di: Wang, Yifei, et al.
Pubblicazione: (2024)

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models
di: Ju, Tianjie, et al.
Pubblicazione: (2024)

Persuasion Tokens for Editing Factual Knowledge in LLMs
di: Youssef, Paul, et al.
Pubblicazione: (2026)

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
di: Zhang, Xue, et al.
Pubblicazione: (2024)

FAME: Towards Factual Multi-Task Model Editing
di: Zeng, Li, et al.
Pubblicazione: (2024)

MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language
di: Ali, Muhammad Asif, et al.
Pubblicazione: (2024)

Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks
di: Huang, Gaoxiang, et al.
Pubblicazione: (2025)

Wolf2Pack: The AutoFusion Framework for Dynamic Parameter Fusion
di: Tian, Bowen, et al.
Pubblicazione: (2024)

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline
di: Lu, Meng, et al.
Pubblicazione: (2025)

Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
di: Xu, Derong, et al.
Pubblicazione: (2024)

Understanding Factual Recall in Transformers via Associative Memories
di: Nichani, Eshaan, et al.
Pubblicazione: (2024)

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
di: Liu, Yihong, et al.
Pubblicazione: (2026)

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
di: Calderon, Nitay, et al.
Pubblicazione: (2026)

Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
di: Qi, Zehan, et al.
Pubblicazione: (2024)

Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation
di: Dejl, Adam, et al.
Pubblicazione: (2025)

KCS: Diversify Multi-hop Question Generation with Knowledge Composition Sampling
di: Wang, Yangfan, et al.
Pubblicazione: (2025)

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
di: Chughtai, Bilal, et al.
Pubblicazione: (2024)

StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall
di: Wu, Yerong, et al.
Pubblicazione: (2026)

Locating and Editing Factual Associations in Mamba
di: Sharma, Arnab Sen, et al.
Pubblicazione: (2024)

Can VLMs Recall Factual Associations From Visual References?
di: Ashok, Dhananjay, et al.
Pubblicazione: (2025)

Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
di: Jafari, Nazanin, et al.
Pubblicazione: (2026)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
di: Lv, Ang, et al.
Pubblicazione: (2024)

Localizing Factual Inconsistencies in Attributable Text Generation
di: Cattan, Arie, et al.
Pubblicazione: (2024)

Can GRPO Boost Complex Multimodal Table Understanding?
di: Kang, Xiaoqiang, et al.
Pubblicazione: (2025)

Multi-hop Reasoning via Early Knowledge Alignment
di: Wang, Yuxin, et al.
Pubblicazione: (2025)

Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?
di: Modica, Luca, et al.
Pubblicazione: (2026)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
di: Lai, Songning, et al.
Pubblicazione: (2024)

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
di: Fastowski, Alina, et al.
Pubblicazione: (2025)

Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
di: Smith, Matthew L., et al.
Pubblicazione: (2026)

Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation
di: Dang, Renfei, et al.
Pubblicazione: (2025)

MultiCube-RAG for Multi-hop Question Answering
di: Shi, Jimeng, et al.
Pubblicazione: (2026)

Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering
di: Chu, Zheng, et al.
Pubblicazione: (2025)