Imagen de Portada

Mitigating Copy Bias in In-Context Learning through Neuron Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ali, Ameen, Wolf, Lior, Titov, Ivan
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models
por: Ali, Ameen, et al.
Publicado: (2025)

Finding Culture-Sensitive Neurons in Vision-Language Models
por: Zhao, Xiutian, et al.
Publicado: (2025)

Suppressing VLM Hallucinations with Spectral Representation Filtering
por: Ali, Ameen, et al.
Publicado: (2025)

Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
por: Yang, Nakyeong, et al.
Publicado: (2023)

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

Cache & Distil: Optimising API Calls to Large Language Models
por: Ramírez, Guillem, et al.
Publicado: (2023)

Mitigating Bias in RAG: Controlling the Embedder
por: Kim, Taeyoun, et al.
Publicado: (2025)

The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
por: Jung, Hoin, et al.
Publicado: (2026)

Shared Doubt: Zero-shot Cross-Lingual Confidence Estimation for Language Models
por: Kyriakou, Athina, et al.
Publicado: (2026)

Joint Localization and Activation Editing for Low-Resource Fine-Tuning
por: Lai, Wen, et al.
Publicado: (2025)

DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning
por: Tyagi, Abhishek, et al.
Publicado: (2026)

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
por: Anagnostidis, Sotiris, et al.
Publicado: (2023)

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
por: Le, Qi, et al.
Publicado: (2025)

Mitigating Gender Bias in Contextual Word Embeddings
por: Yarrabelly, Navya, et al.
Publicado: (2024)

Language Model-Driven Data Pruning Enables Efficient Active Learning
por: Azeemi, Abdul Hameed, et al.
Publicado: (2024)

Bias in Large Language Models: Origin, Evaluation, and Mitigation
por: Guo, Yufei, et al.
Publicado: (2024)

Diagnosing and Mitigating System Bias in Self-Rewarding RL
por: Tan, Chuyi, et al.
Publicado: (2025)

In-Context Learning through the Bayesian Prism
por: Panwar, Madhur, et al.
Publicado: (2023)

DSO: Direct Steering Optimization for Bias Mitigation
por: Paes, Lucas Monteiro, et al.
Publicado: (2025)

Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training
por: Cunegatti, Elia, et al.
Publicado: (2024)

A Representation-Level Assessment of Bias Mitigation in Foundation Models
por: Nizhnichenkov, Svetoslav, et al.
Publicado: (2026)

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
por: Jhaveri, Ayush Rajesh, et al.
Publicado: (2026)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
por: Katz, Shahar, et al.
Publicado: (2024)

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
por: Zimerman, Itamar, et al.
Publicado: (2024)

EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models
por: Rajabzadeh, Hossein, et al.
Publicado: (2024)

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
por: Hellwig, Philipp, et al.
Publicado: (2026)

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies
por: Ma, Sibo, et al.
Publicado: (2025)

Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
por: Hu, Jingyu, et al.
Publicado: (2025)

Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
por: Vargas, Francisco, et al.
Publicado: (2020)

Decomposing Attention To Find Context-Sensitive Neurons
por: Gibson, Alex
Publicado: (2025)

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

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning
por: Kabra, Sanchit, et al.
Publicado: (2025)

Mitigating Bias for Question Answering Models by Tracking Bias Influence
por: Ma, Mingyu Derek, et al.
Publicado: (2023)

Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias
por: Cunningham, Eoghan, et al.
Publicado: (2025)

Learn it or Leave it: Module Composition and Pruning for Continual Learning
por: Wang, Mingyang, et al.
Publicado: (2024)

A Contrastive Learning Approach to Mitigate Bias in Speech Models
por: Koudounas, Alkis, et al.
Publicado: (2024)

Understanding and Mitigating Tokenization Bias in Language Models
por: Phan, Buu, et al.
Publicado: (2024)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
por: Huang, Yanwen, et al.
Publicado: (2025)

LLM Questionnaire Completion for Automatic Psychiatric Assessment
por: Rosenman, Gony, et al.
Publicado: (2024)

A data science and machine learning approach to continuous analysis of Shakespeare's plays
por: Swisher, Charles, et al.
Publicado: (2023)