8 papers
Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM
Luo Ji, Qi Qin, Ningyuan Xi +3
Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on L…
TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition
Ningyuan Xi, Hao Xu, Hongsheng Xin +1
Large language models (LLMs) have made remarkable progress in reasoning tasks, largely driven by post-training paradigms, especially reinforcement learning with verifiable rewards…
MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning
Ningyuan Xi, Xiaoyu Wang, Yetao Wu +7
Current research efforts are focused on enhancing the thinking and reasoning capability of large language model (LLM) by prompting, data-driven emergence and inference-time computa…
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…
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…
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…