REVIEW 8 cited by
In-Context Retrieval-Augmented Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition, they can mitigate the problem of factually inaccurate text generation and provide natural source attribution mechanism. Existing RALM approaches focus on modifying the LM architecture in order to facilitate the incorporation of external information, significantly complicating deployment. This paper considers a simple alternative, which we dub In-Context RALM: leaving the LM architecture unchanged and prepending grounding documents to the input, without any further training of the LM. We show that In-Context RALM that builds on off-the-shelf general purpose retrievers provides surprisingly large LM gains across model sizes and diverse corpora. We also demonstrate that the document retrieval and ranking mechanism can be specialized to the RALM setting to further boost performance. We conclude that In-Context RALM has considerable potential to increase the prevalence of LM grounding, particularly in settings where a pretrained LM must be used without modification or even via API access.
Forward citations
Cited by 8 Pith papers
-
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
On an enterprise corpus scaled from 1.7M to 601M tokens, BM25 beats raw-file agentic search, dense retrieval, and graph RAG at large sizes, crossing near 10M tokens.
-
Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
A training-free closed-form alignment of retrieved windows outperforms a trained fusion adapter on frozen time-series foundation models.
-
Shifting from Ranking to Set Selection for Retrieval Augmented Generation
SETR identifies a query's information requirements with chain-of-thought reasoning and selects a compact passage set, improving multi-hop RAG accuracy over fixed-top-k reranking baselines.
-
HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation
A hierarchical chain-of-thought instruction-tuning curriculum for filtering, combination, and reasoning improves zero-shot retrieval-augmented QA.
-
SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence
SelfElicit uses deep-layer attention to automatically highlight relevant evidence sentences in the input context, yielding consistent QA accuracy gains across six instruction-tuned LLMs.
-
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
A unified benchmark comparing RAG knowledge-extraction attacks and defenses, showing query diversity boosts extraction, embedding attacks fail to transfer, and graph indexing raises per-token leakage.
-
On the Merits of LLM-Based Corpus Enrichment
LLM-generated, query-biased documents added to a search corpus improve retrieval effectiveness, RAG answer accuracy, and answer attribution in proof-of-concept experiments that use oracle-selected source documents.
-
Structured Relevance Assessment for Robust Retrieval-Augmented Language Models
A retrieval-augmented framework that scores document relevance, balances internal and external knowledge, and abstains when uncertain, claims to cut hallucinations, but the reported evidence is thin and inconsistent.
Discussion (0). Continue with ORCID to comment.