14 citations · 40 across the 12 of their papers we have counts for
3 papers · 1 filter
Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation
Tathagata Raha, Clement Christophe, Nada Saadi +4
Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. We adapt the Cross-Examination Framework (CEF) for a reference-free,…
Overalignment in Frontier LLMs: An Empirical Study of Sycophantic Behaviour in Healthcare
Clément Christophe, Wadood Mohammed Abdul, Prateek Munjal +3
As LLMs are increasingly integrated into clinical workflows, their tendency for sycophancy, prioritizing user agreement over factual accuracy, poses significant risks to patient sa…
Do Instruction-Tuned Models Always Perform Better Than Base Models? Evidence from Math and Domain-Shifted Benchmarks
Prateek Munjal, Clement Christophe, Ronnie Rajan +1
Instruction finetuning is standard practice for improving LLM performance, yet it remains unclear whether it enhances reasoning or merely induces surface-level pattern matching. We…