9 papers
MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation
Yangsong Lan, Renkai Hu, HongKai Zheng +4
Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning. However, distilling such traj…
DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
Yixin Bu, Runze Xia, Guanyun Zou +3
Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the mo…
Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection
Qiuyuan Li, Hongliang Dai, Piji Li
Existing hallucination detection methods are typically conducted at the inference stage, without making any modifications to the model itself. In this paper, we are interested in e…
CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning
Yangsong Lan, Hongliang Dai, Piji Li
Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. While prior works attempt to c…
M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models
Zexuan Li, Hongliang Dai, Piji Li
For Relation Extraction (RE), the manual annotation of training data may be prohibitively expensive, since the sentences that contain the target relations in texts can be very scar…
Generating Diverse Training Samples for Relation Extraction with Large Language Models
Zexuan Li, Hongliang Dai, Piji Li
Using Large Language Models (LLMs) to generate training data can potentially be a preferable way to improve zero or few-shot NLP tasks. However, many problems remain to be investig…
Characteristic AI Agents via Large Language Models
Xi Wang, Hongliang Dai, Shen Gao +1
The advancement of Large Language Models (LLMs) has led to significant enhancements in the performance of chatbot systems. Many researchers have dedicated their efforts to the deve…
An Empirical Investigation of Domain Adaptation Ability for Chinese Spelling Check Models
Xi Wang, Ruoqing Zhao, Hongliang Dai +1
Chinese Spelling Check (CSC) is a meaningful task in the area of Natural Language Processing (NLP) which aims at detecting spelling errors in Chinese texts and then correcting thes…
Medical Report Generation based on Segment-Enhanced Contrastive Representation Learning
Ruoqing Zhao, Xi Wang, Hongliang Dai +2
Automated radiology report generation has the potential to improve radiology reporting and alleviate the workload of radiologists. However, the medical report generation task poses…