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,
Linq-Embed-Mistral technical report
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.
KD-Judge structures fitness rules via LLM retrieval and chain-of-thought, then uses pose-guided kinematics for rule-based rep validation with caching for efficient edge deployment, achieving RTF < 1 and speedups up to 15.91x on Jetson.
Fine-tuned recurrent models like Mamba2 produce competitive text embeddings with linear-time constant-memory inference via vertical chunking, outperforming transformers in memory use.
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,
-
Task-Adaptive Embedding Refinement via Test-time LLM Guidance
Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.
-
KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices
KD-Judge structures fitness rules via LLM retrieval and chain-of-thought, then uses pose-guided kinematics for rule-based rep validation with caching for efficient edge deployment, achieving RTF < 1 and speedups up to 15.91x on Jetson.
-
Linear-Time and Constant-Memory Text Embeddings Based on Recurrent Language Models
Fine-tuned recurrent models like Mamba2 produce competitive text embeddings with linear-time constant-memory inference via vertical chunking, outperforming transformers in memory use.