LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
Santhanam , author O
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
XTR training does not improve retrieval effectiveness over ColBERT but enhances IVF engine efficiency by flattening token scores to produce more discriminative centroids.
A Voronoi cell estimation framework in embedding space enables principled token pruning for late-interaction models, reducing index size while retaining retrieval quality.
Hard maximum similarity pooling in late-interaction models induces higher patch-level gradient concentration and greater length sensitivity than top-k or softmax alternatives.
HHEM delivers fast hallucination detection in LLMs via classification, cutting evaluation time from 8 hours to 10 minutes with up to 82.2% accuracy while adding segment retrieval for summarization.
citing papers explorer
-
On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
-
A Replicability Study of XTR
XTR training does not improve retrieval effectiveness over ColBERT but enhances IVF engine efficiency by flattening token scores to produce more discriminative centroids.
-
A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models
A Voronoi cell estimation framework in embedding space enables principled token pruning for late-interaction models, reducing index size while retaining retrieval quality.
-
Spike Hijacking in Late-Interaction Retrieval
Hard maximum similarity pooling in late-interaction models induces higher patch-level gradient concentration and greater length sensitivity than top-k or softmax alternatives.
-
Hallucination Detection and Evaluation of Large Language Model
HHEM delivers fast hallucination detection in LLMs via classification, cutting evaluation time from 8 hours to 10 minutes with up to 82.2% accuracy while adding segment retrieval for summarization.