Imagen de Portada

Drift: Decoding-time Personalized Alignments with Implicit User Preferences

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Minbeom, Lee, Kang-il, Joo, Seongho, Lee, Hwaran, Thonet, Thibaut, Jung, Kyomin
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

Guaranteed Generation from Large Language Models
por: Kim, Minbeom, et al.
Publicado: (2024)

LifeTox: Unveiling Implicit Toxicity in Life Advice
por: Kim, Minbeom, et al.
Publicado: (2023)

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
por: Min, Kyungmin, et al.
Publicado: (2024)

AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
por: Kim, Minbeom, et al.
Publicado: (2024)

VLind-Bench: Measuring Language Priors in Large Vision-Language Models
por: Lee, Kang-il, et al.
Publicado: (2024)

Program Synthesis via Test-Time Transduction
por: Lee, Kang-il, et al.
Publicado: (2025)

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
por: Joo, Seongho, et al.
Publicado: (2025)

Public Data Assisted Differentially Private In-Context Learning
por: Joo, Seongho, et al.
Publicado: (2025)

A Character-Centric Creative Story Generation via Imagination
por: Park, Kyeongman, et al.
Publicado: (2024)

FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
por: Thonet, Thibaut, et al.
Publicado: (2025)

Alignment Data Map for Efficient Preference Data Selection and Diagnosis
por: Lee, Seohyeong, et al.
Publicado: (2025)

Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
por: Joo, Seongho, et al.
Publicado: (2025)

ReflectCAP: Detailed Image Captioning with Reflective Memory
por: Min, Kyungmin, et al.
Publicado: (2026)

Personalized LLM Decoding via Contrasting Personal Preference
por: Bu, Hyungjune, et al.
Publicado: (2025)

Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
por: Hwang, Yerin, et al.
Publicado: (2025)

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
por: Kim, Jeonghye, et al.
Publicado: (2025)

Persona Switch: Mixing Distinct Perspectives in Decoding Time
por: Kim, Junseok, et al.
Publicado: (2026)

ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models
por: Thonet, Thibaut, et al.
Publicado: (2024)

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge
por: Lee, Jiyoung, et al.
Publicado: (2024)

Can You Trick the Grader? Adversarial Persuasion of LLM Judges
por: Hwang, Yerin, et al.
Publicado: (2025)

Fine-grained Gender Control in Machine Translation with Large Language Models
por: Lee, Minwoo, et al.
Publicado: (2024)

Avoidance Decoding for Diverse Multi-Branch Story Generation
por: Park, Kyeongman, et al.
Publicado: (2025)

When Wording Steers the Evaluation: Framing Bias in LLM judges
por: Hwang, Yerin, et al.
Publicado: (2026)

Findings of the Third Automatic Minuting (AutoMin) Challenge
por: Shinde, Kartik, et al.
Publicado: (2025)

Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
por: Koh, Hyukhun, et al.
Publicado: (2024)

Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation
por: Lee, Dongryeol, et al.
Publicado: (2026)

MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers
por: Park, Kyeongman, et al.
Publicado: (2025)

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
por: Lee, Sangmook, et al.
Publicado: (2025)

Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
por: Lee, Dongryeol, et al.
Publicado: (2024)

Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
por: Moon, Jiwon, et al.
Publicado: (2025)

Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
por: Lee, Dongryeol, et al.
Publicado: (2024)

Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
por: Kim, Junseok, et al.
Publicado: (2024)

MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty
por: Yang, Yongjin, et al.
Publicado: (2024)

Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding
por: Yoo, Haneul, et al.
Publicado: (2024)

Conditional [MASK] Discrete Diffusion Language Model
por: Koh, Hyukhun, et al.
Publicado: (2024)

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

Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation
por: Kim, Jieyong, et al.
Publicado: (2024)

Multi-Drafter Speculative Decoding with Alignment Feedback
por: Kim, Taehyeon, et al.
Publicado: (2026)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
por: Kim, Dongyoung, et al.
Publicado: (2024)

From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
por: Li, Jia-Nan, et al.
Publicado: (2025)