Projects

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
Benchmark for evaluating LVLMs on visual perception questions on scientific figures.
Dec 1, 2024
VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
Critical Survey of Self-Correction of LLMs
We critically survey broad papers and discuss the conditions required for successful self-correction.
Jun 3, 2024
Critical Survey of Self-Correction of LLMs
ReaLMistake: Benchmark for Evaluating LLMs at Detecting Errors in LLM Responses
Benchmark including errors in responses of GPT-4 and Llama 2 70B annotated by experts.
Apr 4, 2024
ReaLMistake: Benchmark for Evaluating LLMs at Detecting Errors in LLM Responses