Ningyuan Xi
YOU?
Author Swipe
View article: Making Language Model a Hierarchical Classifier
Making Language Model a Hierarchical Classifier Open
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 decoder architecture could be built with different layers decodi…
View article: Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling Open
View article: Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval
Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval Open
Despite the recent advancement in Retrieval-Augmented Generation (RAG) systems, most retrieval methodologies are often developed for factual retrieval, which assumes query and positive documents are semantically similar. In this paper, we …
View article: Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation
Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation Open
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 applications in such scenarios including multi-personal meetin…
View article: MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning
MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning Open
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 computation. In this study, we consider stimulating language model…
View article: LaMsS: When Large Language Models Meet Self-Skepticism
LaMsS: When Large Language Models Meet Self-Skepticism Open
Hallucination is a major challenge for large language models (LLMs), preventing their further application in some fields. The skeptical thinking of humankind could be useful for LLMs to self-cognition, self-reflection and alleviate their h…
View article: A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio
A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio Open
Large Language Models (LLM) often need to be Continual Pre-Trained (CPT) to obtain unfamiliar language skills or adapt to new domains. The huge training cost of CPT often asks for cautious choice of key hyper-parameters such as the mixture…
View article: Surfactant Protein-C Regulates Alveolar Type 2 Epithelial Cell Lineages via the CD74 Receptor
Surfactant Protein-C Regulates Alveolar Type 2 Epithelial Cell Lineages via the CD74 Receptor Open
This study suggests that SPC regulates AT2 lineage in vitro and in vivo. The SPC might influence AT2 lineage during the lung epithelium repair by activating signaling mechanism involving CD74 receptor.