15 citations · 17 across the 7 of their papers we have counts for
7 papers · 1 filter
Refusal Direction is Universal Across Safety-Aligned Languages
Xinpeng Wang, Mingyang Wang, Yihong Liu +2
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in ac…
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Xinpeng Wang, Chengzhi Hu, Paul Röttger +1
Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful…
"Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?
Beiduo Chen, Xinpeng Wang, Siyao Peng +3
Human label variation (HLV) is a valuable source of information that arises when multiple human annotators provide different labels for valid reasons. In Natural Language Inference…
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
Xinpeng Wang, Chengzhi Hu, Bolei Ma +2
Multiple choice questions (MCQs) are commonly used to evaluate the capabilities of large language models (LLMs). One common way to evaluate the model response is to rank the candid…
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Xinpeng Wang, Bolei Ma, Chengzhi Hu +5
The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice qu…
ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation
Xinpeng Wang, Barbara Plank
Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent s…