Noiser: Bounded Input Perturbations for Attributing Large Language Models
Feature attribution (FA) methods are common post-hoc approaches that explain how Large Language Models (LLMs) make predictions. Generating faithful at…
Learning GUI Grounding with Spatial Reasoning from Visual Feedback
Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task — given a natural language instruction, generate on-screen coordinates …
An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
Large Language Models (LLMs) frequently produce factually inaccurate outputs—a phenomenon known as hallucination—which limits their accuracy in knowle…
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
Autoregressive language models rely on a Key-Value (KV) Cache to avoid re-computing past hidden states during generation. As model sizes and context l…
MedSyn: Enhancing Diagnostics with Human-AI Collaboration
Clinical decision-making is inherently complex, often influenced by cognitive biases, incomplete information, and case ambiguity. Large Language Models (LLMs) have shown promise …
PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting …
PosterSum: A Multimodal Benchmark for Scientific Poster Summarization
Generating accurate and concise textual summaries from multimodal documents is challenging, especially when dealing with visually complex content like…
Inverse Scaling in Test-Time Compute
We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse sc…
Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs
Understanding time from visual representations is a fundamental cognitive skill, yet it remains a challenge for multimodal large language models (MLLM…