Read original ↗

paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering

Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted. With a growing share of question answering systems built on top of commercial language model APIs, a method that can decide how much to retrieve, and how far to trust its own answers, without retraining the underlying model, is of clear practical value

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

LinkedLinked via unknownRAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P] →
LinkedLinked via unknownKnowledge Distillation of Black-Box Large Language Models →
PossiblePossibly related (embedding) · 55%amscotti/local-LLM-with-RAG →
PossiblePossibly related (embedding) · 49%NirDiamant/RAG_Techniques →
PossiblePossibly related (embedding) · 47%telekom/wurzel →
PossiblePossibly related (embedding) · 58%Lynavo/lynavo-drive →
PossiblePossibly related (embedding) · 48%Loop Engineering for RAG Question Parsing: The Small Loop That Runs Before Retrieval - towardsdatascience.com →
PossiblePossibly related (embedding) · 55%We’ve got a workshop on production retrieval-augmented generation with open models, benchmarked end to end, thought it’d be relevant here [D] →

Covers

newsRAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P]newsKnowledge Distillation of Black-Box Large Language Models

Implements (incoming)

repoamscotti/local-LLM-with-RAG repoNirDiamant/RAG_Techniques repotelekom/wurzel repoLynavo/lynavo-drive

Covers (incoming)

newsLoop Engineering for RAG Question Parsing: The Small Loop That Runs Before Retrieval - towardsdatascience.com newsWe’ve got a workshop on production retrieval-augmented generation with open models, benchmarked end to end, thought it’d be relevant here [D]

Related across the graph

newsWe’ve got a workshop on production retrieval-augmented generation with open models, benchmarked end to end, thought it’d be relevant here [D]newsKnowledge Distillation of Black-Box Large Language Models newsLoop Engineering for RAG Question Parsing: The Small Loop That Runs Before Retrieval - towardsdatascience.com repoLynavo/lynavo-drive repotelekom/wurzel newsRAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P]repoamscotti/local-LLM-with-RAG repoNirDiamant/RAG_Techniques

Topics