Imagen de Portada

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lv, Ang, Chen, Yuhan, Zhang, Kaiyi, Wang, Yulong, Liu, Lifeng, Wen, Ji-Rong, Xie, Jian, Yan, Rui
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

An Analysis and Mitigation of the Reversal Curse
por: Lv, Ang, et al.
Publicado: (2023)

Geometric Factual Recall in Transformers
por: Ravfogel, Shauli, et al.
Publicado: (2026)

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

Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
por: Zhang, Kaiyi, et al.
Publicado: (2024)

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

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

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

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

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

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
por: Li, Junyi, et al.
Publicado: (2024)

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

Language Models "Grok" to Copy
por: Lv, Ang, et al.
Publicado: (2024)

Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning
por: Wang, Yulong, et al.
Publicado: (2024)

Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
por: Ren, Ruiyang, et al.
Publicado: (2023)

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

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
por: Das, Souvik, et al.
Publicado: (2024)

How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective
por: Liu, Qi, et al.
Publicado: (2025)

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
por: Chen, Changyu, et al.
Publicado: (2024)

CodeSimpleQA: Scaling Factuality in Code Large Language Models
por: Yang, Jian, et al.
Publicado: (2025)

HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
por: Chen, Yuhan, et al.
Publicado: (2024)

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
por: Yang, Jiayu, et al.
Publicado: (2025)

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration
por: Wu, Songhao, et al.
Publicado: (2025)

Co-occurrence is not Factual Association in Language Models
por: Zhang, Xiao, et al.
Publicado: (2024)

UFO: a Unified and Flexible Framework for Evaluating Factuality of Large Language Models
por: Huang, Zhaoheng, et al.
Publicado: (2024)

Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
por: Chen, Yuhan, et al.
Publicado: (2023)

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

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
por: Lin, Hongzhan, et al.
Publicado: (2024)

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

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

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
por: Zhang, Kaiyi, et al.
Publicado: (2025)

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
por: Liu, Langming, et al.
Publicado: (2026)

Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling
por: Lee, Hyunji, et al.
Publicado: (2025)

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

Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
por: Saynova, Denitsa, et al.
Publicado: (2024)

Fine-Tuning Dynamics of In-Context Factual Recall in Transformers
por: Huang, Ruomin, et al.
Publicado: (2026)

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

Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules
por: Gong, Zhuocheng, et al.
Publicado: (2024)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
por: Wang, Mingyang, et al.
Publicado: (2025)

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

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