all AI news
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Feb. 23, 2024, 5:48 a.m. | Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul R\"ottger, Frauke Kreuter, Dirk Hovy, Barbara Plank
cs.CL updates on arXiv.org arxiv.org
Abstract: The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice questions (MCQ) to limit the response space. The model is then evaluated by ranking the candidate answers by the log probability of the first token prediction. However, first-tokens may not consistently reflect the final response output, due to model's diverse response styles such as starting with "Sure" or refusing to answer. Consequently, MCQ …
abstract arxiv cs.cl evaluation instruction-tuned language language generation language models large language large language models llms match multiple nature questions ranking space text token type
More from arxiv.org / cs.CL updates on arXiv.org
ALBA: Adaptive Language-based Assessments for Mental Health
2 days, 18 hours ago |
arxiv.org
PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
2 days, 18 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US