9 papers
Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe +6
Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through inference-ti…
Early Stopping for Large Reasoning Models via Confidence Dynamics
Parsa Hosseini, Sumit Nawathe, Mahdi Salmani +2
Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade p…
Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception
Yize Cheng, Arshia Soltani Moakhar, Chenrui Fan +5
Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlooked limitation of these agents is…
GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
Aryan Yazdan Parast, Parsa Hosseini, Hesam Asadollahzadeh +4
Object hallucination in Multimodal Large Language Models (MLLMs) is a persistent failure mode that causes the model to perceive objects absent in the image. This weakness of MLLMs…
Clinical Semantic Intelligence (CSI): Emulating the Cognitive Framework of the Expert Clinician for Comprehensive Oral Disease Diagnosis
Mohammad Mashayekhi, Sara Ahmadi Majd, Arian AmirAmjadi +1
The diagnosis of oral diseases presents a problematic clinical challenge, characterized by a wide spectrum of pathologies with overlapping symptomatology. To address this, we devel…
Tool Preferences in Agentic LLMs are Unreliable
Kazem Faghih, Wenxiao Wang, Yize Cheng +5
Large language models (LLMs) can now access a wide range of external tools, thanks to the Model Context Protocol (MCP). This greatly expands their abilities as various agents. Howe…
Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption
Wenxiao Wang, Parsa Hosseini, Soheil Feizi
Chain-of-thought prompting has demonstrated great success in facilitating the reasoning abilities of large language models. In this work, we explore how these enhanced reasoning ab…
SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs
Parsa Hosseini, Sumit Nawathe, Mazda Moayeri +2
Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite lan…
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
Fahimeh Hosseini Noohdani, Parsa Hosseini, Aryan Yazdan Parast +2
While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samp…