4 papers
Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs
Tanya Chowdhury, Atharva Nijasure, Yair Zick +1
Fine-tuned Large Language Models (LLMs) encode rich task-specific features, but the form of these representations, especially within MLP layers, remains unclear. Empirical inspecti…
How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs
Atharva Nijasure, Tanya Chowdhury, James Allan
We conduct a behavioral exploration of LoRA fine-tuned LLMs for Passage Reranking to understand how relevance signals are learned and deployed by Large Language Models. By fine-tun…
Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval
Tanya Chowdhury, Atharva Nijasure, James Allan
Transformer networks, particularly those achieving performance comparable to GPT models, are well known for their robust feature extraction abilities. However, the nature of these…
RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank
Tanya Chowdhury, Yair Zick, James Allan
Numerous works propose post-hoc, model-agnostic explanations for learning to rank, focusing on ordering entities by their relevance to a query through feature attribution methods.…