Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds | Paper Citation Record

Observation 453231b0-dd6c-47f8-97c6-6bd69634cc52 · outbound

This paper cites Transformers learn to implement preconditioned gradient descent for in-context learning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Transformers learn to implement preconditioned gradient descent for in-context learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:38.500659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45a1687-cc6b-472b-a295-d96a8ab9402f · outbound

This paper cites Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:38.556369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae6b730b-8b0c-40a9-8b6e-f883b0fa0bb9 · outbound

This paper cites an unresolved cited work.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:17:46.201071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c6c3f1ab-e9e0-4cd3-83a2-804af817ac31 · outbound

This paper cites Language models are few-shot learners.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Language models are few-shot learners

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:38.709435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5335d914-4217-4fd5-abad-66813c612fcf · outbound

This paper cites Reading Wikipedia to Answer Open-Domain Questions.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Reading Wikipedia to Answer Open-Domain Questions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:38.785951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de69886a-61fa-4b3a-b4d8-f0dd7865cb5b · outbound

This paper cites Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:46.038349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3b5a508e-e388-40b4-b000-cfe8134fc9b3 · outbound

This paper cites Exploring the robustness of in-context learning with noisy labels.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Exploring the robustness of in-context learning with noisy labels

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.895129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0c486fa1-47fe-41f7-b8d4-bcf6a3a86513 · outbound

This paper cites UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.040515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a493d251-38bf-49d2-b6b1-e99e41d2cb69 · outbound

This paper cites Nearest neighbor pattern classification.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Nearest neighbor pattern classification

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.115206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 665515ca-40a5-4881-8ea7-faf5803e9c18 · outbound

This paper cites A Survey on In-context Learning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds A Survey on In-context Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.183271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c602aa6d-77ec-4ff2-8bc8-af68576c139a · outbound

This paper cites A survey on in-context learning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds A survey on in-context learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.725354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 840fb628-5f38-4624-a3b5-9bf6d78b589f · outbound

This paper cites What can transformers learn in-context? a case study of simple function classes.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds What can transformers learn in-context? a case study of simple function classes

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.360691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d9aa306-04bc-44ce-a708-e74dd9e788eb · outbound

This paper cites Test-time training provably improves transformers as in-context learners.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Test-time training provably improves transformers as in-context learners

Reference 13

Resolution: verified exact; raw_fallback, observed 2026-08-07T11:17:43.595950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c0685d4a-5851-48c7-acdd-f77629b34f50 · outbound

This paper cites RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.504967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bdfadf8-3fa8-4e56-b3f5-3d7cc433f6a5 · outbound

This paper cites Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.603008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d01428-8d7e-4927-ab98-25cb0cef8690 · outbound

This paper cites On a formula for the product-moment coefficient of any order of a normal frequency distribution in any number of variables.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds On a formula for the product-moment coefficient of any order of a normal frequency distribution in any number of variables

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.580317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d8dd8265-2981-4b8d-910e-7a57b831a05f · outbound

This paper cites Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.723732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d61b5b7a-5c9b-4a01-b039-7cf6c39b3e1f · outbound

This paper cites Atlas: Few-shot Learning with Retrieval Augmented Language Models.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Atlas: Few-shot Learning with Retrieval Augmented Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.810318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec128c8e-0ae9-46c8-bec4-6310b8f23cce · outbound

This paper cites T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.902007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb981af-fd87-4946-b411-22fffa6b63c4 · outbound

This paper cites Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:39.983797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9475e65c-a6be-46b8-a2d2-2305ba6e4f0c · outbound

This paper cites Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.053099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36165c48-c10a-4f71-9ce9-979ac74dabc4 · outbound

This paper cites More documents, same length: Isolating the challenge of multiple documents in rag.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds More documents, same length: Isolating the challenge of multiple documents in rag

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.131615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47f14b3-99be-496d-a913-60ab1a41a104 · outbound

This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt\.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt\

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.430098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c4568230-0fe3-4b57-a029-f567d944d674 · outbound

This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.269002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 552e2383-c110-4de2-a501-79ae26c5c545 · outbound

This paper cites Making large language models a better foundation for dense retrieval.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Making large language models a better foundation for dense retrieval

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.369301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e3e34b3-2ead-4733-95aa-1fd357d1d141 · outbound

This paper cites Self-Prompting Large Language Models for Zero-Shot Open-Domain QA.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Self-Prompting Large Language Models for Zero-Shot Open-Domain QA

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.447199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc3be01-c182-4957-b963-50c32cb59d89 · outbound

This paper cites Mot: Pre-thinking and recalling enable chatgpt to self-improve with memory-of-thoughts.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Mot: Pre-thinking and recalling enable chatgpt to self-improve with memory-of-thoughts

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.123763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 872e96f7-0091-4311-8f0d-bbeb3ff991c8 · outbound

This paper cites Chain-of-knowledge: Grounding large language models via dynamic knowledge adapting over heterogeneous sources.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Chain-of-knowledge: Grounding large language models via dynamic knowledge adapting over heterogeneous sources

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:45.001137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e4904414-3f30-4017-a16b-a98c5c49f3af · outbound

This paper cites What Makes Good In-Context Examples for GPT-$3$?.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds What Makes Good In-Context Examples for GPT-$3$?

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.688811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd067063-b0f8-4f55-a7cb-7b0b545e97d1 · outbound

This paper cites In-context Learning with Retrieved Demonstrations for Language Models: A Survey.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds In-context Learning with Retrieved Demonstrations for Language Models: A Survey

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.744158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0e8bb2-d755-4654-8a0c-9d1ac34f48e3 · outbound

This paper cites Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:40.862413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1936a5bd-40ab-4c5d-afa8-34a9e09ed084 · outbound

This paper cites Sfr-embedding-mistral:enhance text retrieval with transfer learning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Sfr-embedding-mistral:enhance text retrieval with transfer learning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:44.848808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 99f9f3df-09e5-44a6-b359-82d11c0c5746 · outbound

This paper cites MetaICL: Learning to Learn In Context.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds MetaICL: Learning to Learn In Context

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:41.052656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935c02eb-c88c-4aef-bca1-fdf2c16cffd9 · outbound

This paper cites The matrix cookbook.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds The matrix cookbook

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:44.675277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2e416a7a-4703-4175-82fd-0d1f5e49f6d8 · outbound

This paper cites In-context retrieval-augmented language models.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds In-context retrieval-augmented language models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:44.498703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e443f08c-ab00-49fb-94a2-1ea1de7d2457 · outbound

This paper cites Smallcap: Lightweight image captioning prompted with retrieval augmentation.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Smallcap: Lightweight image captioning prompted with retrieval augmentation

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:44.341800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e596ff2a-ed2a-47b4-8700-709d2c5fb36f · outbound

This paper cites Retrieval-augmented transformer for image captioning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Retrieval-augmented transformer for image captioning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:44.186752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 342aa257-ef0e-4c8b-89dd-10ea763c529a · outbound

This paper cites XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:17:42.982988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e661e810-7120-410f-a6a3-d2e4e31443dd · outbound

This paper cites Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:41.569413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5346b35-224c-428d-bca0-fbc0dd17e265 · outbound

This paper cites Can In-context Learning Really Generalize to Out-of-distribution Tasks?.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Can In-context Learning Really Generalize to Out-of-distribution Tasks?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:41.632679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7862e33e-dc62-43bd-9192-131a0aa39c32 · outbound

This paper cites Certifiably robust rag against retrieval corruption.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Certifiably robust rag against retrieval corruption

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:41.716891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dac30df0-a7e3-4574-8529-13ad7a03afcc · outbound

This paper cites An Explanation of In-context Learning as Implicit Bayesian Inference.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds An Explanation of In-context Learning as Implicit Bayesian Inference

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:41.814337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a408d94-4550-4828-b903-615f277a3121 · outbound

This paper cites RECOMP : Improving retrieval-augmented LM s with context compression and selective augmentation.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds RECOMP : Improving retrieval-augmented LM s with context compression and selective augmentation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:44.006795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c2ed5542-c425-40bb-902f-434ced401127 · outbound

This paper cites Is Retriever Merely an Approximator of Reader?.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Is Retriever Merely an Approximator of Reader?

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:42.003536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 504bdad9-5f44-4d46-942b-8ff747489115 · outbound

This paper cites Compositional exemplars for in-context learning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Compositional exemplars for in-context learning

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:43.846537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d54ed430-e86f-4d44-9091-ceea372959c4 · outbound

This paper cites Making Retrieval-Augmented Language Models Robust to Irrelevant Context.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Making Retrieval-Augmented Language Models Robust to Irrelevant Context

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:42.164458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3845079c-5d56-4fcf-a55a-40e2d4d1e956 · outbound

This paper cites Trained transformers learn linear models in-context.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Trained transformers learn linear models in-context

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:42.238089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2d55af-4d18-4142-b4f0-cb2d681259d0 · outbound

This paper cites Automatic Chain of Thought Prompting in Large Language Models.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Automatic Chain of Thought Prompting in Large Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:42.323534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb610021-4f19-4822-8653-f6736cefce14 · outbound

This paper cites Retrieval-Augmented Generation for AI-Generated Content: A Survey.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds Retrieval-Augmented Generation for AI-Generated Content: A Survey

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:42.362748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5980e085-0b6c-4107-a5e2-98834121e438 · outbound

This paper cites NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:17:42.636941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers