Image de couverture de livre

KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Seorin, Lee, Dongyoung, Lee, Jaejin
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SEDD: Scalable and Efficient Dataset Deduplication with GPUs
par: Son, Youngjun, et autres
Publié: (2025)

Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs
par: Ji, SeungWon, et autres
Publié: (2025)

Models Know Models Best: Evaluation via Model-Preferred Formats
par: Lee, Joonhak, et autres
Publié: (2026)

ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models
par: Han, Hojae, et autres
Publié: (2024)

Thunder-Tok: Minimizing Tokens per Word in Tokenizing Korean Texts for Generative Language Models
par: Cho, Gyeongje, et autres
Publié: (2025)

Red-Teaming for Inducing Societal Bias in Large Language Models
par: Luo, Chu Fei, et autres
Publié: (2024)

RefineBench: Evaluating Refinement Capability of Language Models via Checklists
par: Lee, Young-Jun, et autres
Publié: (2025)

Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs
par: Chae, Kyubyung, et autres
Publié: (2025)

Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments
par: Hahm, Sungeun, et autres
Publié: (2025)

Reasoning by Commented Code for Table Question Answering
par: Pyo, Seho, et autres
Publié: (2026)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
par: Kim, Dongyoung, et autres
Publié: (2024)

A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models
par: Sathe, Ashutosh, et autres
Publié: (2024)

Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation
par: Lee, Nakyung, et autres
Publié: (2025)

CUE-M: Contextual Understanding and Enhanced Search with Multimodal Large Language Model
par: Go, Dongyoung, et autres
Publié: (2024)

Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space
par: Park, Seongmin, et autres
Publié: (2024)

On The Conceptualization and Societal Impact of Cross-Cultural Bias
par: Bhandari, Vitthal
Publié: (2025)

DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
par: Han, Hojae, et autres
Publié: (2026)

Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding
par: Jung, Sungmok, et autres
Publié: (2026)

Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
par: Kim, Taehyeon, et autres
Publié: (2023)

Choices Speak Louder than Questions
par: Cho, Gyeongje, et autres
Publié: (2025)

Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
par: So, Yeonkyoung, et autres
Publié: (2025)

Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages
par: Gamboa, Lance Calvin Lim, et autres
Publié: (2025)

PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation
par: Yoo, Jaeseok, et autres
Publié: (2024)

Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT
par: Lee, Wonhyuk, et autres
Publié: (2025)

Detecting Bias in Large Language Models: Fine-tuned KcBERT
par: Lee, J. K., et autres
Publié: (2024)

Social Bias in Multilingual Language Models: A Survey
par: Gamboa, Lance Calvin Lim, et autres
Publié: (2025)

Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models
par: Lee, Younghun, et autres
Publié: (2024)

Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data
par: Lee, Younghun, et autres
Publié: (2024)

Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads
par: Yang, Yi, et autres
Publié: (2023)

Robust Bias Evaluation with FilBBQ: A Filipino Bias Benchmark for Question-Answering Language Models
par: Gamboa, Lance Calvin Lim, et autres
Publié: (2026)

Interpreting Bias in Large Language Models: A Feature-Based Approach
par: Prakash, Nirmalendu, et autres
Publié: (2024)

Structured Language Generation Model: Loss Calibration and Formatted Decoding for Robust Structure Prediction and Knowledge Retrieval
par: Lee, Minho, et autres
Publié: (2024)

Small Language Models are Equation Reasoners
par: Kim, Bumjun, et autres
Publié: (2024)

Large Language Models as Search Engines: Societal Challenges
par: Sadeddine, Zacchary, et autres
Publié: (2025)

Refining Time Series Anomaly Detectors using Large Language Models
par: Yang, Alan, et autres
Publié: (2025)

SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation
par: Kim, Jungwoo, et autres
Publié: (2025)

Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources
par: Kim, Jinpyo, et autres
Publié: (2025)

Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
par: Yu, Sangwon, et autres
Publié: (2024)

Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
par: Park, Bumjin, et autres
Publié: (2025)

Selective Generation for Controllable Language Models
par: Lee, Minjae, et autres
Publié: (2023)