sin-bench-tracing-native-evidence-chains-in-long

Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic 'Needle-In-A-Haystack' tests often reward answer matching without requiring a causal, evidence-linked reasoning trace in the document. We propose the 'Fish-in-the-Ocean' (FITO) paradigm, which requires model…

Independent GitHub snapshot · Automated classification · Original documentation governs