9 papers
Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS
Yue Zhao, Hongyan Li, Yong Chen +1
Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the streaming text-to-speech (TTS) syn…
Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Models
Qingqing Gu, Dan Wang, Yue Zhao +5
Chain-of-Thought (CoT) is widely applied to enhance the LLM capability in math, coding and reasoning tasks. However, its performance is limited for open-domain tasks, when there ar…
Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
Yue Zhao, Xiaoyu Wang, Dan Wang +7
World models have been widely utilized in robotics, gaming, and auto-driving. However, their applications on natural language tasks are relatively limited. In this paper, we constr…
Making Language Model a Hierarchical Classifier
Yihong Wang, Zhonglin Jiang, Ningyuan Xi +8
Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decod…
Convert Language Model into a Value-based Strategic Planner
Xiaoyu Wang, Yue Zhao, Qingqing Gu +4
Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained re…
EmoFSM: A Finite State Machine for Emotional Support Conversation
Yue Zhao, Qingqing Gu, Xiaoyu Wang +5
Emotional support conversation (ESC) aims to alleviate people's emotional distress through effective conversations. Although large language models (LLMs) have made remarkable progr…
Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval
Luo Ji, Feixiang Guo, Teng Chen +9
Despite the recent advancement in Retrieval-Augmented Generation (RAG) systems, most retrieval methodologies are often developed for factual retrieval, which assumes query and posi…
Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation
Xiaoyu Wang, Ningyuan Xi, Teng Chen +6
Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their app…
M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture
Hongyang Lei, Xiaolong Cheng, Qi Qin +8
Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but m…