4 papers
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…
Beyond Metrics: A Critical Analysis of the Variability in Large Language Model Evaluation Frameworks
Marco AF Pimentel, Clément Christophe, Tathagata Raha +3
As large language models (LLMs) continue to evolve, the need for robust and standardized evaluation benchmarks becomes paramount. Evaluating the performance of these models is a co…
Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches
Clément Christophe, Praveen K Kanithi, Prateek Munjal +13
This study presents a comprehensive analysis and comparison of two predominant fine-tuning methodologies - full-parameter fine-tuning and parameter-efficient tuning - within the co…