← Back to all news

Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

6,381 stories · RSS feed

arXiv Computation and Language
Sep 1

When Can We Work in Embedding Space? What Text Embeddings Preserve

The paper investigates when text embeddings can be reliably used as inputs for empirical analysis by formalizing the assumption that embeddings preserve essential information from the original text. Under a generative model where documents are mixtures of latent topics, the author examines two applications: clustering documents in embedding space and using embeddings as controls for high‑dimensional text. Empirical results on 363 U.S. metropolitan areas show that clusters derived from LLM‑generated economic descriptions capture interpretable economic archetypes and better distinguish local employment dynamics than alternative clustering methods or curated covariates.

By Simon Freyaldenhoven
llmsrag
More like this →
arXiv Computation and Language
Sep 1

PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models

PEPPER (PErcePtion-Guided PERturbation) is a backdoor defense for text-to-image diffusion models that rewrites input captions into semantically distant yet visually similar versions, adding unobtrusive elements to disrupt trigger embeddings. By escaping the attacked neighborhood in the text embedding space, PEPPER reduces attack success, especially against text encoder-based attacks, while preserving generation quality. The method requires no training or model weight access and can be combined with existing defenses to achieve stronger, generalizable robustness.

By Oscar Chew, Po-Yi Lu, Jayden Lin, Kuan-Hao Huang, Hsuan-Tien Lin
ragdiffusion
More like this →
arXiv AI
Sep 1

Reverse N-Wise Output-Oriented Testing for AI/ML and Quantum Computing Systems

The paper proposes reverse n‑wise output‑oriented testing for AI/ML and quantum computing systems, a method that builds covering arrays over output equivalence classes, confidence buckets, decision boundaries, fairness partitions, embedding clusters, ranking stability bands, quantum measurement distributions, and error syndrome patterns. It then uses gradient‑free metaheuristic optimization to solve the inverse mapping problem, generating input configurations or quantum circuit parameters that trigger specific behavioral signatures in opaque models. The framework claims to provide explicit coverage guarantees, higher fault detection rates for calibration, boundary, and error syndromes, improved test suite efficiency, and automated partition discovery for MLOps and quantum validation pipelines.

By Lamine Rihani
ragsafety
More like this →
arXiv AI
Sep 1

Efficient GPU Retrieval for Semantic Search

The paper introduces a GPU‑optimized retrieval framework for LinkedIn’s semantic search, partitioning embeddings into eight category‑supervised segments and applying a min/median aggregation rule aligned with the existing relevance policy. A lightweight Stage‑1 scorer generates high‑recall candidates, while a two‑stage GPU architecture—FP8 coarse ranking followed by FP16 re‑ranking—boosts throughput and recall, achieving 99.6‑99.8% of full‑FP16 recall at over 500 QPS per shard. In A/B testing, the system raises exploratory‑query Precision@10 from 63.7% to 79.0% and navigational Precision@1 from 65.5% to 74.7%, with human evaluation confirming the improvement.

By Dhritiman Das, Chujie Zheng, Ronak Kaoshik, Pratik Dixit, Vishal Shah, Yanbo Li, Jiahao Xu, Manika Agarwal, Chinmay Naik, Lingyu Zhang, Chetan Bhole, Chirag Bhanuprasad Mehta, Meng Zheng, Puneet Singh Ahluwalia, Shirisha Singh, Ping Jin, Manas Apte, Gokulraj Mohanasundaram, Tugrul Bingol, Raghavan Muthuregunathan, Fedor Borisyuk
llmsragefficiency
More like this →