11 papers
Multi-Objective Exploration and Preference Optimization via Mutual Information
Hongyan Xie, Yikun Ban, Ruiyu Fang +4
Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Cu…
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
Shuo Nie, Hexuan Deng, Chao Wang +6
As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings…
Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking
Haoxiang Su, Ruiyu Fang, Liting Jiang +2
The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions.…
A benchmark for joint dialogue satisfaction, emotion recognition, and emotion state transition prediction
Jing Bian, Haoxiang Su, Liting Jiang +6
User satisfaction is closely related to enterprises, as it not only directly reflects users' subjective evaluation of service quality or products, but also affects customer loyalty…
UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment
Hongyan Xie, Yikun Ban, Ruiyu Fang +6
Multi-objective alignment aims to align LLM responses with multiple human preference objectives. Among existing methods, guiding the generation of frozen LLMs through autoregressiv…
Training Report of TeleChat3-MoE
Xinzhang Liu, Chao Wang, Zhihao Yang +51
TeleChat3-MoE is the latest series of TeleChat large language models, featuring a Mixture-of-Experts (MoE) architecture with parameter counts ranging from 105 billion to over one t…