Spectral Tempering derives an adaptive scaling factor γ(k) from the embedding eigenspectrum via local SNR analysis and knee-point normalization to achieve near-optimal compression without training or validation.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.
Peerispect extracts claims from peer reviews, retrieves evidence from the manuscript, and verifies them via NLI in a modular pipeline with a visual interface.
Reproducibility study confirms Hypencoder's non-linear query-specific scoring improves retrieval over bi-encoders on standard benchmarks but standard methods remain faster and hard-task results are mixed due to implementation issues.
citing papers explorer
-
Spectral Tempering for Embedding Compression in Dense Passage Retrieval
Spectral Tempering derives an adaptive scaling factor γ(k) from the embedding eigenspectrum via local SNR analysis and knee-point normalization to achieve near-optimal compression without training or validation.
-
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
-
100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
-
REMOD: Relation Extraction for Modeling Online Discourse
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.
-
Peerispect: Claim Verification in Scientific Peer Reviews
Peerispect extracts claims from peer reviews, retrieves evidence from the manuscript, and verifies them via NLI in a modular pipeline with a visual interface.
-
Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval
Reproducibility study confirms Hypencoder's non-linear query-specific scoring improves retrieval over bi-encoders on standard benchmarks but standard methods remain faster and hard-task results are mixed due to implementation issues.