4 papers
EviRerank: Adaptive Evidence Construction for Long-Document LLM Reranking
Minghan Li, Eric Gaussier, Juntao Li +1
Decoder-only LLM rerankers struggle with long documents: inference is costly and relevance signals can be diluted by irrelevant context. Motivated by a diagnostic attention analysi…
DRIV-EX: Counterfactual Explanations for Driving LLMs
Amaia Cardiel, Eloi Zablocki, Elias Ramzi +1
Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process…
GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers
Ãloi Zablocki, Valentin Gerard, Amaia Cardiel +3
Understanding the decision processes of deep vision models is essential for their safe and trustworthy deployment in real-world settings. Existing explainability approaches, such a…
Efficient Long-Document Reranking via Block-Level Embeddings and Top-k Interaction Refinement
Minghan Li, Eric Gaussier, Guodong Zhou
Dense encoders and LLM-based rerankers struggle with long documents: single-vector representations dilute fine-grained relevance, while cross-encoders are often too expensive for p…