Paper Citation Record · LEDGER

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models

As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.00049.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.00049 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:05:42.701392Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact2
verified fuzzy13
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 31a1e125-14d3-4314-b7b8-d0ce3b8f122f · outbound

This paper cites ChatGPT Alternative Solutions: Large Language Models Survey.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models ChatGPT Alternative Solutions: Large Language Models Survey

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:05:43.476742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 48c871dd-3118-416e-ba71-42379cd18677 · outbound

This paper cites Combining Static and Contextualised Multilingual Embeddings.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Combining Static and Contextualised Multilingual Embeddings

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:05:43.332228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 69b7eb3c-dbed-4cc7-8cb8-2a1958bfa02d · outbound

This paper cites Generative multi-modal knowledge retrieval with large language models,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Generative multi-modal knowledge retrieval with large language models,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.579319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1e93cc45-a067-4251-824d-c2de0e46ffa2 · outbound

This paper cites Combining Knowledge Graphs and Large Language Models.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Combining Knowledge Graphs and Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:41.050595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92cbe90f-510c-490c-a674-7ab8ba60dc44 · outbound

This paper cites Semantic-embedding guided graph network for cross-modal retrieval,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Semantic-embedding guided graph network for cross-modal retrieval,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.445148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 797a1782-feae-4760-8c76-eac93bc8096c · outbound

This paper cites ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:41.309394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea6ed0f-9e02-4c22-a61d-72acefeb5ef1 · outbound

This paper cites ColBERTv2: Effective and efficient retrieval via lightweight late interaction,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models ColBERTv2: Effective and efficient retrieval via lightweight late interaction,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.298622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation be6ae041-01f0-4bfd-a37a-b5d76022754a · outbound

This paper cites COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.143268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8d613c87-3c9f-4028-988f-8b1aa4e86deb · outbound

This paper cites DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:41.558233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041522bf-7e3d-4ceb-902f-b92a69374429 · outbound

This paper cites Sentence-BERT: Sentence embeddings using siamese BERT-networks,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Sentence-BERT: Sentence embeddings using siamese BERT-networks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.975123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 00fa5ffa-7c4c-4d59-8579-ad63777af205 · outbound

This paper cites Dense passage retrieval for open-domain question answering,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Dense passage retrieval for open-domain question answering,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.817932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 75d83684-6b32-46ca-8b94-4493f755110e · outbound

This paper cites Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:05:43.124640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 37b280df-10ba-4b49-84eb-61f776cc094a · outbound

This paper cites Scaling Laws for Neural Language Models.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Scaling Laws for Neural Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:41.854282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 829130c8-465c-4f31-be5b-c83ed67923ab · outbound

This paper cites RetroMAE: Pre-training retrieval-oriented language models with masked auto-encoder.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models RetroMAE: Pre-training retrieval-oriented language models with masked auto-encoder

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.623052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eb679451-4adf-4706-a9b6-c4393949b7af · outbound

This paper cites Precise Zero-Shot Dense Retrieval without Relevance Labels.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Precise Zero-Shot Dense Retrieval without Relevance Labels

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:42.001955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 370b4999-05c5-46d0-b90e-bb6e3162f65a · outbound

This paper cites Varied phenomenology of models displaying dynamical large-deviation singularities.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Varied phenomenology of models displaying dynamical large-deviation singularities

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:05:42.939787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 678d33a2-c5a8-4af4-bcb6-181ac9822bf1 · outbound

This paper cites MiniLM: Deep self-attention distillation for task-agnostic compression of pre- trained transformers,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models MiniLM: Deep self-attention distillation for task-agnostic compression of pre- trained transformers,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.483135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eb68fc14-87d2-44af-8b2b-463c0639f213 · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:42.234451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72f9dd12-b14f-4708-b074-e54ec352d3d5 · outbound

This paper cites Retrieval augmented generation or long-context LLMs? A comprehensive study and hybrid approach,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Retrieval augmented generation or long-context LLMs? A comprehensive study and hybrid approach,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.355358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ae578d0b-31d7-4a57-a4ab-1069181bf991 · outbound

This paper cites Blended RAG: Improving RAG (retriever-augmented generation) accuracy with semantic search and hybrid query-based retrievers,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Blended RAG: Improving RAG (retriever-augmented generation) accuracy with semantic search and hybrid query-based retrievers,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.177604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c9b5c3a-2cfa-4868-8c6c-5ebac555c91d · outbound

This paper cites Self-RAG: Learning to retrieve, generate, and critique through self-reflection.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Self-RAG: Learning to retrieve, generate, and critique through self-reflection

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.011927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 68f7d33b-86a6-4456-8997-b6f2fbd0e020 · outbound

This paper cites Few-shot learning with retrieval-augmented language models,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Few-shot learning with retrieval-augmented language models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.830554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c1c6dac0-e024-4d0e-93ec-412e708a696c · outbound

This paper cites Generalization through Memorization: Nearest Neighbor Language Models.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models Generalization through Memorization: Nearest Neighbor Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:42.586334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57eccb2d-6dca-401b-bb9a-eba4ad1b45da · outbound

This paper cites A graph based document retrieval method,.

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models A graph based document retrieval method,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.581691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.