Copertina

SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM Inference

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Luyang, Wang, Jialu, Zhu, Shichao, Li, Beibei, Wang, Zhongcun, Pan, Guangmou, Song, Yang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Aligning Language Models with Human Preferences via a Bayesian Approach
di: Wang, Jiashuo, et al.
Pubblicazione: (2023)

Fairshare Data Pricing via Data Valuation for Large Language Models
di: Zhang, Luyang, et al.
Pubblicazione: (2025)

Dissecting Human and LLM Preferences
di: Li, Junlong, et al.
Pubblicazione: (2024)

Improving LLM-as-a-Judge Inference with the Judgment Distribution
di: Wang, Victor, et al.
Pubblicazione: (2025)

BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference
di: Zhao, Junqi, et al.
Pubblicazione: (2024)

Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
di: Li, Jingxuan, et al.
Pubblicazione: (2024)

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
di: Wang, Yinjie, et al.
Pubblicazione: (2025)

LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue
di: Wang, Jinqiang, et al.
Pubblicazione: (2025)

CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
di: Su, Jinyan, et al.
Pubblicazione: (2026)

Probability-Consistent Preference Optimization for Enhanced LLM Reasoning
di: Yang, Yunqiao, et al.
Pubblicazione: (2025)

Effectively Steer LLM To Follow Preference via Building Confident Directions
di: Song, Bingqing, et al.
Pubblicazione: (2025)

User-LLM: Efficient LLM Contextualization with User Embeddings
di: Ning, Lin, et al.
Pubblicazione: (2024)

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
di: Yang, Zhengbang, et al.
Pubblicazione: (2026)

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
di: Wang, Jiashuo, et al.
Pubblicazione: (2025)

Do Agents Repair When Challenged -- or Just Reply? Challenge, Repair, and Public Correction in a Deployed Agent Forum
di: Zhang, Luyang, et al.
Pubblicazione: (2026)

Users as Annotators: LLM Preference Learning from Comparison Mode
di: Cai, Zhongze, et al.
Pubblicazione: (2025)

Reading Users' Minds from What They Say: An Investigation into LLM-based Empathic Mental Inference
di: Zhu, Qihao, et al.
Pubblicazione: (2024)

Scaling LLM Inference with Optimized Sample Compute Allocation
di: Zhang, Kexun, et al.
Pubblicazione: (2024)

LRHP: Learning Representations for Human Preferences via Preference Pairs
di: Wang, Chenglong, et al.
Pubblicazione: (2024)

NeuronMLP: Efficient LLM Inference via Singular Value Decomposition Compression and Tiling on AWS Trainium
di: Song, Dinghong, et al.
Pubblicazione: (2025)

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
di: Xu, Huimin, et al.
Pubblicazione: (2025)

DPO-Shift: Shifting the Distribution of Direct Preference Optimization
di: Yang, Xiliang, et al.
Pubblicazione: (2025)

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs
di: Zhang, Rongzhi, et al.
Pubblicazione: (2024)

No Preference Left Behind: Group Distributional Preference Optimization
di: Yao, Binwei, et al.
Pubblicazione: (2024)

Latent Inter-User Difference Modeling for LLM Personalization
di: Qiu, Yilun, et al.
Pubblicazione: (2025)

Efficient Long-Context LLM Inference via KV Cache Clustering
di: Hu, Jie, et al.
Pubblicazione: (2025)

Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models
di: Li, Shengzhi, et al.
Pubblicazione: (2024)

Aligning Large Language Models with Implicit Preferences from User-Generated Content
di: Tan, Zhaoxuan, et al.
Pubblicazione: (2025)

AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference
di: Lin, Fangzhou, et al.
Pubblicazione: (2026)

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
di: Chen, Yizhuo, et al.
Pubblicazione: (2025)

LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation
di: Li, Jinze, et al.
Pubblicazione: (2026)

ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
di: Wang, Hao, et al.
Pubblicazione: (2026)

Beyond the Surface: Measuring Self-Preference in LLM Judgments
di: Chen, Zhi-Yuan, et al.
Pubblicazione: (2025)

ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
di: Tian, Yuanhe, et al.
Pubblicazione: (2023)

DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering
di: Wang, Qing, et al.
Pubblicazione: (2026)

Mitigating KV Cache Competition to Enhance User Experience in LLM Inference
di: Shen, Haiying, et al.
Pubblicazione: (2025)

Nash CoT: Multi-Path Inference with Preference Equilibrium
di: Zhang, Ziqi, et al.
Pubblicazione: (2024)

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
di: She, Shuaijie, et al.
Pubblicazione: (2025)

Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings
di: Liu, Xuanqing, et al.
Pubblicazione: (2025)

Judging with Confidence: Calibrating Autoraters to Preference Distributions
di: Li, Zhuohang, et al.
Pubblicazione: (2025)