Jamshid Mozafari
3 papers · Latest:
Natural Language Processing
Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
Q-DAPS estimates LLM question difficulty by analyzing the entropy of answer plausibility scores, outperforming baselines and aligning with human judgment.
2605.12398
Natural Language ProcessingPretraining Exposure Explains Popularity Judgments in Large Language Models
LLMs' popularity judgments are primarily driven by pretraining data exposure, not external popularity, as shown by analyzing OLMo and Dolma.
2605.12382
Natural Language ProcessingContext Convergence Improves Answering Inferential Questions
This paper shows that constructing passages with high "context convergence" significantly improves LLM accuracy on inferential question answering tasks.
2605.12370
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.