Imagen de Portada

Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ji, SeungWon, Lee, Jungyup, Kim, Jemin, Park, Sang, Lee, SeungJae
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Making Qwen3 Think in Korean with Reinforcement Learning
por: Lee, Jungyup, et al.
Publicado: (2025)

DNA 1.0 Technical Report
por: Lee, Jungyup, et al.
Publicado: (2025)

Has R&D investment become riskier for CEOs after the Sarbanes Oxley Act?
por: SeungWon Lee
Publicado: (2024)

A Mean-Reverting Model of Exchange Rate Risk Premium Using Ornstein-Uhlenbeck Dynamics
por: Hwang, SeungJae
Publicado: (2025)

How Language Directions Align with Token Geometry in Multilingual LLMs
por: Kim, JaeSeong, et al.
Publicado: (2025)

REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents using Information Relevance and Relative Proximity
por: Seo, SeungWon, et al.
Publicado: (2024)

Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation
por: Shabalin, Alexander, et al.
Publicado: (2025)

TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data
por: Kim, Seung-Bin, et al.
Publicado: (2024)

ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs
por: Yoo, HanGyeol, et al.
Publicado: (2026)

From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
por: Seo, SeungWon, et al.
Publicado: (2026)

KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models
por: Kim, Seorin, et al.
Publicado: (2025)

Heteroatom‐Embedded Spiro[Fluorene‐9,9′‐Xanthene]‐Based Electron Transport Materials for Improved Driving Voltage and Efficiency in Phosphorescent Organic Light‐Emitting Diodes
por: Byeonghun Kim, et al.
Publicado: (2024)

A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency
por: Park, Sihyeong, et al.
Publicado: (2025)

Social Bias in Multilingual Language Models: A Survey
por: Gamboa, Lance Calvin Lim, et al.
Publicado: (2025)

Investigating Language Preference of Multilingual RAG Systems
por: Park, Jeonghyun, et al.
Publicado: (2025)

Controlling Language Confusion in Multilingual LLMs
por: Lee, Nahyun, et al.
Publicado: (2025)

Language Bias under Conflicting Information in Multilingual LLMs
por: Östling, Robert, et al.
Publicado: (2026)

Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean
por: Choi, ChangSu, et al.
Publicado: (2024)

Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models
por: Kim, Ju-Young, et al.
Publicado: (2025)

Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusion
por: Park, Jeonghyun, et al.
Publicado: (2026)

Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learning
por: Park, Seong-Il, et al.
Publicado: (2024)

Disentangling Questions from Query Generation for Task-Adaptive Retrieval
por: Lee, Yoonsang, et al.
Publicado: (2024)

Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant
por: Lee, Jemin, et al.
Publicado: (2024)

Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editing
por: Noh, Seongrae, et al.
Publicado: (2026)

BridG MT: Enhancing LLMs' Machine Translation Capabilities with Sentence Bridging and Gradual MT
por: Choi, Seung-Woo, et al.
Publicado: (2024)

MultiPragEval: Multilingual Pragmatic Evaluation of Large Language Models
por: Park, Dojun, et al.
Publicado: (2024)

Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia
por: Gamboa, Lance Calvin Lim, et al.
Publicado: (2024)

AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
por: Lee, Sangjun, et al.
Publicado: (2025)

Chaining Event Spans for Temporal Relation Grounding
por: Kim, Jongho, et al.
Publicado: (2025)

QwenLong-CPRS: Towards $\infty$-LLMs with Dynamic Context Optimization
por: Shen, Weizhou, et al.
Publicado: (2025)

Framing Political Bias in Multilingual LLMs Across Pakistani Languages
por: Nadeem, Afrozah, et al.
Publicado: (2025)

Ideological Bias in LLMs' Economic Causal Reasoning
por: Lee, Donggyu, et al.
Publicado: (2026)

Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models
por: Balasubramanian, Sriram, et al.
Publicado: (2025)

A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia
por: Gamboa, Lance Calvin Lim, et al.
Publicado: (2024)

Bias in, Bias out: Annotation Bias in Multilingual Large Language Models
por: Cui, Xia, et al.
Publicado: (2025)

Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models
por: Kim, Jongho, et al.
Publicado: (2025)

KiC: Keyword-inspired Cascade for Cost-Efficient Text Generation with LLMs
por: Kim, Woo-Chan, et al.
Publicado: (2025)

Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
por: Park, Bumjin, et al.
Publicado: (2025)

LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
por: Kim, Dongjun, et al.
Publicado: (2026)

Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models
por: Shin, Jisu, et al.
Publicado: (2024)