2 citations · 4 across the 10 of their papers we have counts for
12 papers
When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment
Zhaohan Zhang, Junjie Liu, Chengzhengxu Li +6
The reasoning trajectory of a Large Language Model (LLM) is often treated as a verbalized description of its internal reasoning. However, such trajectories can be unfaithful: a mod…
MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors
Yuanfan Li, Qi Zhou, Chengzhengxu Li +5
We present MGTEVAL, an extensible platform for systematic evaluation of Machine-Generated Text (MGT) detectors. Despite rapid progress in MGT detection, existing evaluations are of…
Confidence Should Be Calibrated More Than One Turn Deep
Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu +3
Large Language Models (LLMs) are increasingly applied in high-stakes domains such as finance, healthcare, and education, where reliable multi-turn interactions with users are essen…
DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection
Guoxin Ma, Xiaoming Liu, Hongyang Chen +6
Detecting machine-generated text has become a critical challenge amid the rapid advancement of LLMs, yet existing detectors degrade severely under domain shift. Through systematic…
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang +5
Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing w…
Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training
Yuanfan Li, Zhaohan Zhang, Chengzhengxu Li +2
Machine-generated Text (MGT) detection is crucial for regulating and attributing online texts. While the existing MGT detectors achieve strong performance, they remain vulnerable t…
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang +4
Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts…
StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation
Xiaoming Liu, Chen Liu, Zhaohan Zhang +4
Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this appr…
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
Yichen Wang, Shangbin Feng, Abe Bohan Hou +5
The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress tes…
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better
Shengchao Liu, Xiaoming Liu, Yichen Wang +5
The burgeoning generative capabilities of large language models (LLMs) have raised growing concerns about abuse, demanding automatic machine-generated text detectors. DetectGPT, a…
Improving Pacing in Long-Form Story Planning
Yichen Wang, Kevin Yang, Xiaoming Liu +1
Existing LLM-based systems for writing long-form stories or story outlines frequently suffer from unnatural pacing, whether glossing over important events or over-elaborating on in…
Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning
Chengzhengxu Li, Xiaoming Liu, Yichen Wang +3
Prompt-based pre-trained language models (PLMs) paradigm have succeeded substantially in few-shot natural language processing (NLP) tasks. However, prior discrete prompt optimizati…