2 papers
cs.CL2026
Knowing When Not to Answer: Evaluating Abstention in Multimodal Reasoning Systems
Nishanth Madhusudhan, Vikas Yadav, Alexandre Lacoste
Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for reliable multimodal systems. Yet existing evaluation paradigms for visi…
cs.LG2025
Revitalizing Saturated Benchmarks: A Weighted Metric Approach for Differentiating Large Language Model Performance
Bryan Etzine, Masoud Hashemi, Nishanth Madhusudhan +4
Existing benchmarks are becoming saturated and struggle to separate model performances due to factors like data contamination and advancing LLM capabilities. This paper introduces…