Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection
Eli Schwartz
We present our system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. A small (B-parameter) VLM is fine-tuned as a per-token classifier r…
cs.CL2025
Advancing Speech Understanding in Speech-Aware Language Models with GRPO
Avishai Elmakies, Hagai Aronowitz, Nimrod Shabtay +3
In this paper, we introduce a Group Relative Policy Optimization (GRPO)-based method for training Speech-Aware Large Language Models (SALLMs) on open-format speech understanding ta…