activity
20222026
most citedChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

6 citations · 6 across the 7 of their papers we have counts for

collaborators

7 papers

cs.AI2026

HSRM: Hidden-State Reward Models for Test-Time Verification

Xianzhi Li, Xiaodan Zhu

Large language models can often generate plausible mathematical reasoning traces, but reliably identifying the correct solution among multiple candidates remains a key challenge. E…

cs.LG2025

Meta-Learning Reinforcement Learning for Crypto-Return Prediction

Junqiao Wang, Zhaoyang Guan, Guanyu Liu +7

Predicting cryptocurrency returns is notoriously difficult: price movements are driven by a fast-shifting blend of on-chain activity, news flow, and social sentiment, while labeled…

cs.CL2025

Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM Agents

Abdellah Ghassel, Xianzhi Li, Xiaodan Zhu

Large Language Models (LLMs) have demonstrated substantial capabilities in conversational AI applications, yet their susceptibility to dialogue breakdowns poses significant challen…

cs.CL2025

Entropy-Gated Branching for Efficient Test-Time Reasoning

Xianzhi Li, Ethan Callanan, Abdellah Ghassel +1

Test-time compute methods can significantly improve the reasoning capabilities and problem-solving accuracy of large language models (LLMs). However, these approaches require subst…

cs.AI2024

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation

Xianzhi Li, Ran Zmigrod, Zhiqiang Ma +2

Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with…

cs.CL20236 cited

ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

Yihao Fang, Xianzhi Li, Stephen W. Thomas +1

Open intent detection, a crucial aspect of natural language understanding, involves the identification of previously unseen intents in user-generated text. Despite the progress mad…