most citedUnconstrained Monotonic Calibration of Predictions in Deep Ranking Systems

2 citations · 2 across the 8 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2026

Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs

Ziyi Zhao, Chongming Gao, Yang Zhang +5

Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitat…

cs.CL2026

PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models

Chengbing Wang, Wuqiang Zheng, Yang Zhang +5

Large Language Models (LLMs) are increasingly deployed in human-centric applications, yet they often fail to provide substantive emotional support. While Reinforcement Learning (RL…

cs.CL2025

Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation

Chengbing Wang, Yang Zhang, Wenjie Wang +4

Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlookin…

cs.CL2025

SteerX: Disentangled Steering for LLM Personalization

Xiaoyan Zhao, Ming Yan, Yilun Qiu +5

Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life a…

cs.CL2025

Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts

Xiaoyan Zhao, Ming Yan, Yang Zhang +6

Conversational Recommender Systems (CRSs) aim to provide personalized recommendations through multi-turn natural language interactions with users. Given the strong interaction and…

cs.CL2025

Latent Inter-User Difference Modeling for LLM Personalization

Yilun Qiu, Tianhao Shi, Xiaoyan Zhao +3

Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's…