The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yan, Liu, Yu, Chen, Xiaokang, Chen, Pin-Yu, Zan, Daoguang, Kan, Min-Yen, Ho, Tsung-Yi
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment
by: Liu, Yan, et al.
Published: (2024)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
by: Hu, Xiaomeng, et al.
Published: (2024)

Improving Natural Language Capability of Code Large Language Model
by: Li, Wei, et al.
Published: (2024)

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
by: Hu, Xiaomeng, et al.
Published: (2024)

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
by: Hu, Xiaomeng, et al.
Published: (2025)

Mitigating Biases in Language Models via Bias Unlearning
by: Liu, Dianqing, et al.
Published: (2025)

Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
by: Xiong, Chen, et al.
Published: (2025)

On Pre-training of Multimodal Language Models Customized for Chart Understanding
by: Fan, Wan-Cyuan, et al.
Published: (2024)

Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
by: Yu, Zeping, et al.
Published: (2025)

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
by: Chou, Sheng-Yen, et al.
Published: (2023)

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

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
by: Long, Do Xuan, et al.
Published: (2024)

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
by: Xiong, Chen, et al.
Published: (2025)

Mitigating Social Biases in Language Models through Unlearning
by: Dige, Omkar, et al.
Published: (2024)

Examining Forgetting in Continual Pre-training of Aligned Large Language Models
by: Li, Chen-An, et al.
Published: (2024)

Probing Language Models for Pre-training Data Detection
by: Liu, Zhenhua, et al.
Published: (2024)

Retention Score: Quantifying Jailbreak Risks for Vision Language Models
by: Li, Zaitang, et al.
Published: (2024)

Defining and Evaluating Physical Safety for Large Language Models
by: Tang, Yung-Chen, et al.
Published: (2024)

On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena
by: Naous, Tarek, et al.
Published: (2025)

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
by: Yu, Zeping, et al.
Published: (2024)

Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
by: Qian, Chen, et al.
Published: (2024)

Can Pre-trained Language Models Understand Chinese Humor?
by: Chen, Yuyan, et al.
Published: (2024)

Discursive Circuits: How Do Language Models Understand Discourse Relations?
by: Miao, Yisong, et al.
Published: (2025)

TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models
by: Lyu, Chong, et al.
Published: (2025)

Detection, Classification, and Mitigation of Gender Bias in Large Language Models
by: Cheng, Xiaoqing, et al.
Published: (2025)

Model Merging in Pre-training of Large Language Models
by: Li, Yunshui, et al.
Published: (2025)

In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart Understanding
by: Fan, Wan-Cyuan, et al.
Published: (2025)

Projective Methods for Mitigating Gender Bias in Pre-trained Language Models
by: Dawkins, Hillary, et al.
Published: (2024)

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
by: Liu, Shuliang, et al.
Published: (2025)

Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
by: Chen, Meiqi, et al.
Published: (2024)

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

Improving Neuron-level Interpretability with White-box Language Models
by: Bai, Hao, et al.
Published: (2024)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
by: Xiong, Chen, et al.
Published: (2024)

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
by: He, Yu, et al.
Published: (2025)

Robust Evaluation Measures for Evaluating Social Biases in Masked Language Models
by: Liu, Yang
Published: (2024)

Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models
by: Tu, Zhijun, et al.
Published: (2025)

Making Pre-trained Language Models Great on Tabular Prediction
by: Yan, Jiahuan, et al.
Published: (2024)

Improving Long Text Understanding with Knowledge Distilled from Summarization Model
by: Liu, Yan, et al.
Published: (2024)

Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach
by: Zhang, Renhan, et al.
Published: (2025)

DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation
by: Li, Minzhi, et al.
Published: (2024)