6 papers
MIRROR: Learning from the Other View for Multi-Modal Reasoning
Wen Ye, Yuxiao Qu, Aviral Kumar +1
Unlike large language models (LLMs) that exhibit strong reasoning capabilities, vision-language models (VLMs) struggle with visual reasoning, even on geometry problems that admit e…
An Exam for Active Observers
Jiarui Zhang, Muzi Tao, Shangshang Wang +3
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued…
From Reasoning to Pixels: Benchmarking the Alignment Gap in Unified Multimodal Models
Cheng Yang, Chufan Shi, Bo Shui +7
Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations…
Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
Yuehan Qin, Shawn Li, Yi Nian +3
Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially w…
LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems
Nan Xu, Xuezhe Ma
Interestingly, LLMs yet struggle with some basic tasks that humans find trivial to handle, e.g., counting the number of character r's in the word "strawberry". There are several po…
DecoPrompt : Decoding Prompts Reduces Hallucinations when Large Language Models Meet False Premises
Nan Xu, Xuezhe Ma
While large language models (LLMs) have demonstrated increasing power, they have also called upon studies on their hallucinated outputs that deviate from factually correct statemen…