LLMs implicitly plan answer positions during MCQ generation, as shown by predictive signals in hidden representations and controllable shifts via activation steering.
Can multiple- choice questions really be useful in detecting the abilities of llms?
4 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
4
Pith papers citing it
7
external citations · external index
verdicts
UNVERDICTED 4representative citing papers
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
LLM accuracy on reasoning tasks differs significantly by question type, with step-by-step reasoning accuracy often uncorrelated to final answer selection.
GPT-4o and Claude 3.5 Sonnet reach 73.7-74% accuracy on gastroenterology questions; VLMs gain nothing from images and lose accuracy with LLM-generated captions.
citing papers explorer
-
Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation
LLMs implicitly plan answer positions during MCQ generation, as shown by predictive signals in hidden representations and controllable shifts via activation steering.
-
BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
-
Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?
LLM accuracy on reasoning tasks differs significantly by question type, with step-by-step reasoning accuracy often uncorrelated to final answer selection.
-
Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models
GPT-4o and Claude 3.5 Sonnet reach 73.7-74% accuracy on gastroenterology questions; VLMs gain nothing from images and lose accuracy with LLM-generated captions.