5 citations · 5 across the 11 of their papers we have counts for
11 papers
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
Yang Zhao, Yangou Ouyang, Xiao Ding +8
While Hybrid Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become the standard paradigm for training LLM agents, effective mechanisms for data allocation…
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
Yang Zhao, Hepeng Wang, Xiao Ding +8
Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with ver…
Com: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
Kai Xiong, Xiao Ding, Yixin Cao +7
Large language models (LLMs) have mastered abundant simple and explicit commonsense knowledge through pre-training, enabling them to achieve human-like performance in simple common…
CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
Jinglong Gao, Xiao Ding, Lingxiao Zou +2
In-Context Learning (ICL) enhances the performance of large language models (LLMs) with demonstrations. However, obtaining these demonstrations primarily relies on manual effort. I…
ExpeTrans: LLMs Are Experiential Transfer Learners
Jinglong Gao, Xiao Ding, Lingxiao Zou +3
Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial hu…
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
Yang Zhao, Li Du, Xiao Ding +10
Large language models (LLMs) have shown great potential across various industries due to their remarkable ability to generalize through instruction tuning. However, the limited ava…
Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion
Jinglong Gao, Chen Lu, Xiao Ding +3
Event Causality Extraction (ECE) aims at extracting causal event pairs from texts. Despite ChatGPT's recent success, fine-tuning small models remains the best approach for the ECE…
Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
Jinglong Gao, Xiao Ding, Yiming Cui +4
To improve the performance of large language models (LLMs), researchers have explored providing LLMs with textual task-solving experience via prompts. However, they rely on manual…
Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation
Zhouhao Sun, Xiao Ding, Li Du +4
Large language models (LLMs) have achieved significant performance in various natural language reasoning tasks. However, they still struggle with performing first-order logic reaso…
Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation
Jinglong Gao, Xiao Ding, Bing Qin +1
Causal reasoning ability is crucial for numerous NLP applications. Despite the impressive emerging ability of ChatGPT in various NLP tasks, it is unclear how well ChatGPT performs…
DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination
Tingting Wu, Xiao Ding, Hao Zhang +4
Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum le…