{"id":"b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0","title":"Kang and Li propose DeFT-RAG to break multi-hop questions into reusable steps","argument":"In their arXiv abstract, Dingyi Kang and Bingzhe Li propose DeFT-RAG, a retrieval-augmented generation (RAG) framework for multi-hop questions: questions that require combining facts spread across documents. They argue that graph-based RAG can miss the full evidence chain, while iterative RAG often asks the LLM to plan and manage too many steps.\n\nDeFT-RAG generates one self-contained sub-question at a time, using the original question and earlier question-answer pairs. A QA table tracks what has been answered; rule-based updates and a fine-tuned lightweight decision model handle work the authors say need not be done by the LLM. The framework also caches answers and reuses them when a later sub-question has the same meaning.\n\nThe authors report the best accuracy among thirteen baselines on MuSiQue, 2WikiMultiHopQA and HotpotQA with gpt-4o-mini and Qwen3.6, while using fewer input tokens than other iterative methods. In a test sharing a QA cache across 1,000 MuSiQue questions, 23.1% of sub-questions were answered from the cache, reducing LLM calls by 12.9% without lowering accuracy. These results concern the named datasets and model setups; the abstract does not establish performance on other tasks or in deployed systems. How well does DeFT-RAG perform beyond these benchmarks and cache conditions?","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"Evidence is the paper's arXiv abstract, not the full paper; it does not provide experimental details or results beyond the reported benchmarks and cache test. The abstract does not establish how the reported results generalize to other datasets, model setups, or deployed systems.","speaker":{"name":"Kang, Dingyi, Li, Bingzhe","roleAtSource":"Article author"},"source":{"title":"DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2610.37826","publishedAt":"2026-10-27","dateBasis":"Date basis not provided."},"evidence":[{"text":"Kang and Li propose DeFT-RAG, which generates self-contained sub-questions incrementally and reuses answers to address multi-hop questions.","excerpt":"We propose DeFT-RAG, a RAG framework built on three components.","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"},{"text":"The authors say graph-based RAG methods may miss the full evidence chain, while iterative RAG burdens the LLM with planning and tracking tasks.","excerpt":"Graph-based RAG methods retrieve once from the entities a question names and so rarely recover the full evidence chain.","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"},{"text":"The authors report the best accuracy among thirteen baselines on three named datasets, using gpt-4o-mini and Qwen3.6 as backbones.","excerpt":"On MuSiQue, 2WikiMultiHopQA and HotpotQA, DeFT-RAG achieves the best accuracy among thirteen baselines with both gpt-4o-mini and Qwen3.6 as the backbone","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"},{"text":"With a QA cache shared across 1,000 MuSiQue questions, the authors report that 23.1% of sub-questions were answered from the cache and LLM calls fell by 12.9% without lower accuracy.","excerpt":"With a QA cache shared across 1,000 MuSiQue questions, 23.1% of sub-questions are answered from the cache, which reduces LLM calls by 12.9% without lowering accuracy.","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2610.37826","checkedAt":"2026-11-08T00:16:06.523Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well does DeFT-RAG perform beyond the named benchmarks and cache conditions?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Kang and Li propose DeFT-RAG to break multi-hop questions into reusable steps","summary":"In their arXiv abstract, Dingyi Kang and Bingzhe Li propose DeFT-RAG, a retrieval-augmented generation (RAG) framework for multi-hop questions: questions that require combining facts spread across documents. They argue that graph-based RAG can miss the full evidence chain, while iterative RAG often asks the LLM to plan and manage too many steps.\n\nDeFT-RAG generates one self-contained sub-question at a time, using the original question and earlier question-answer pairs. A QA table tracks what has been answered; rule-based updates and a fine-tuned lightweight decision model handle work the authors say need not be done by the LLM. The framework also caches answers and reuses them when a later sub-question has the same meaning.\n\nThe authors report the best accuracy among thirteen baselines on MuSiQue, 2WikiMultiHopQA and HotpotQA with gpt-4o-mini and Qwen3.6, while using fewer input tokens than other iterative methods. In a test sharing a QA cache across 1,000 MuSiQue questions, 23.1% of sub-questions were answered from the cache, reducing LLM calls by 12.9% without lowering accuracy. These results concern the named datasets and model setups; the abstract does not establish performance on other tasks or in deployed systems. How well does DeFT-RAG perform beyond these benchmarks and cache conditions?","question":"How well does DeFT-RAG perform beyond the named benchmarks and cache conditions?","claims":[{"text":"Kang and Li propose DeFT-RAG, which generates self-contained sub-questions incrementally and reuses answers to address multi-hop questions.","excerpt":"We propose DeFT-RAG, a RAG framework built on three components.","support":"source-stated"},{"text":"The authors say graph-based RAG methods may miss the full evidence chain, while iterative RAG burdens the LLM with planning and tracking tasks.","excerpt":"Graph-based RAG methods retrieve once from the entities a question names and so rarely recover the full evidence chain.","support":"source-stated"},{"text":"The authors report the best accuracy among thirteen baselines on three named datasets, using gpt-4o-mini and Qwen3.6 as backbones.","excerpt":"On MuSiQue, 2WikiMultiHopQA and HotpotQA, DeFT-RAG achieves the best accuracy among thirteen baselines with both gpt-4o-mini and Qwen3.6 as the backbone","support":"source-stated"},{"text":"With a QA cache shared across 1,000 MuSiQue questions, the authors report that 23.1% of sub-questions were answered from the cache and LLM calls fell by 12.9% without lower accuracy.","excerpt":"With a QA cache shared across 1,000 MuSiQue questions, 23.1% of sub-questions are answered from the cache, which reduces LLM calls by 12.9% without lowering accuracy.","support":"source-stated"}],"limitations":["Evidence is the paper's arXiv abstract, not the full paper; it does not provide experimental details or results beyond the reported benchmarks and cache test.","The abstract does not establish how the reported results generalize to other datasets, model setups, or deployed systems."],"mediaId":"406f30760c8b39ebc737621233552582ec362f57f8b9b796e4ebf74827ef28a9","correctionReason":null,"id":"b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0","publicationId":"8f27d101-2f07-4890-8dfa-6c56cf8e0301","version":1,"sourceUrl":"https://arxiv.org/abs/2610.37826","sourceTitle":"DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-10-27","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-10-30T06:42:43.400Z","createdAt":"2026-11-08T00:01:11.162Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"406f30760c8b39ebc737621233552582ec362f57f8b9b796e4ebf74827ef28a9","kind":"article","url":"https://arxiv.org/abs/2610.37826","sourceUrl":"https://arxiv.org/abs/2610.37826","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-10-31T09:48:21.139Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2610.37826","checkedAt":"2026-11-08T00:16:06.523Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"406f30760c8b39ebc737621233552582ec362f57f8b9b796e4ebf74827ef28a9","confidence":0.8,"provider":"typesafe","model":"jev-1.13.0","inputHash":"286da027bda537eff1ca34f0a4d154dc4434e54db00603ff97828a122105dee6","decidedAt":"2026-10-31T09:48:22.821Z"},"provenance":{"textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observationId":"6b782356c781f12601956e8edbb913788963ce27eb5cff9685481e1ae3530170","retrievedAt":"2026-10-31T09:48:20.865Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"f81921ed-73de-4a79-8fb2-7766cc7c9584"},"reviewer":{"model":"gpt-6-luna","runId":"2a609297-ff0a-4391-897a-de43d5d8b9bd"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-08T00:01:11.162Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Kang, Dingyi","url":null,"kind":"unknown"},{"name":"Li, Bingzhe","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Kang, Dingyi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kang, Dingyi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.37826","locator":"head/meta[name=author|citation_author]"},"assertionId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-10-31T09:48:20.865Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd","sourceUrl":"https://arxiv.org/abs/2610.37826","contentSha256":"f434a6680cd7e3d405215c2b380dc8c36b2c020a6e98408edc919d31db31e032","textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observedAt":"2026-10-31T09:48:20.865Z"}},{"actor":{"name":"Li, Bingzhe","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Li, Bingzhe","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.37826","locator":"head/meta[name=author|citation_author]"},"assertionId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-10-31T09:48:20.865Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd","sourceUrl":"https://arxiv.org/abs/2610.37826","contentSha256":"f434a6680cd7e3d405215c2b380dc8c36b2c020a6e98408edc919d31db31e032","textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observedAt":"2026-10-31T09:48:20.865Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2610.37826","snapshotId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd","contentSha256":"f434a6680cd7e3d405215c2b380dc8c36b2c020a6e98408edc919d31db31e032","textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observedAt":"2026-10-31T09:48:20.865Z","basis":"publisher-page-metadata","sourceLinks":42,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0/source"}},"canonicalUrl":"https://escapemeridian.com/readings/kang-and-li-propose-deft-rag-to-break-multi-hop-questions-into-b879c3dd","formats":{"html":"/readings/kang-and-li-propose-deft-rag-to-break-multi-hop-questions-into-b879c3dd","markdown":"/readings/kang-and-li-propose-deft-rag-to-break-multi-hop-questions-into-b879c3dd.md","json":"/readings/kang-and-li-propose-deft-rag-to-break-multi-hop-questions-into-b879c3dd.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-rag","name":"Retrieval-augmented generation","explanation":"A setup in which a model first looks up relevant documents and then answers using them.","referenceUrl":"https://developers.google.com/machine-learning/glossary#retrieval-augmented-generation-rag"},{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"},{"id":"term-fine-tuning","name":"Fine-tuning","explanation":"Further training of an existing model to adapt it to a particular task or use.","referenceUrl":"https://developers.google.com/machine-learning/glossary#fine-tuning"},{"id":"term-tokens","name":"Model tokens","explanation":"Small chunks of text, often parts of words, that a language model reads and writes; usage and prices are often counted in tokens.","referenceUrl":"https://developers.google.com/machine-learning/glossary#token"},{"id":"term-benchmark","name":"Benchmark","explanation":"A defined set of tests used to compare systems. Results depend on the tasks and measures selected.","referenceUrl":"https://arxiv.org/abs/2211.09110"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"},{"id":"time","name":"TIME","kind":"organization","context":"TIME is a news magazine publishing reporting on world affairs, business, technology and the workers behind digital services.","referenceUrls":["https://time.com/"],"path":"/entities/time","json":"/entities/time.json","markdown":"/entities/time.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0","revision":"8f27d101-2f07-4890-8dfa-6c56cf8e0301","revisionKind":"publication-id","title":"Kang and Li propose DeFT-RAG to break multi-hop questions into reusable steps","url":"https://escapemeridian.com/readings/kang-and-li-propose-deft-rag-to-break-multi-hop-questions-into-b879c3dd"},"source":{"type":"source","id":"https://arxiv.org/abs/2610.37826","revision":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","revisionKind":"sha256-source-text","title":"DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers","url":"https://arxiv.org/abs/2610.37826"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0","title":"Kang and Li propose DeFT-RAG to break multi-hop questions into reusable steps","argument":"In their arXiv abstract, Dingyi Kang and Bingzhe Li propose DeFT-RAG, a retrieval-augmented generation (RAG) framework for multi-hop questions: questions that require combining facts spread across documents. They argue that graph-based RAG can miss the full evidence chain, while iterative RAG often asks the LLM to plan and manage too many steps.\n\nDeFT-RAG generates one self-contained sub-question at a time, using the original question and earlier question-answer pairs. A QA table tracks what has been answered; rule-based updates and a fine-tuned lightweight decision model handle work the authors say need not be done by the LLM. The framework also caches answers and reuses them when a later sub-question has the same meaning.\n\nThe authors report the best accuracy among thirteen baselines on MuSiQue, 2WikiMultiHopQA and HotpotQA with gpt-4o-mini and Qwen3.6, while using fewer input tokens than other iterative methods. In a test sharing a QA cache across 1,000 MuSiQue questions, 23.1% of sub-questions were answered from the cache, reducing LLM calls by 12.9% without lowering accuracy. These results concern the named datasets and model setups; the abstract does not establish performance on other tasks or in deployed systems. How well does DeFT-RAG perform beyond these benchmarks and cache conditions?","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"Evidence is the paper's arXiv abstract, not the full paper; it does not provide experimental details or results beyond the reported benchmarks and cache test. The abstract does not establish how the reported results generalize to other datasets, model setups, or deployed systems.","speaker":{"name":"Kang, Dingyi, Li, Bingzhe","roleAtSource":"Article author"},"source":{"title":"DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2610.37826","publishedAt":"2026-10-27","dateBasis":"Date basis not provided."},"evidence":[{"text":"Kang and Li propose DeFT-RAG, which generates self-contained sub-questions incrementally and reuses answers to address multi-hop questions.","excerpt":"We propose DeFT-RAG, a RAG framework built on three components.","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"},{"text":"The authors say graph-based RAG methods may miss the full evidence chain, while iterative RAG burdens the LLM with planning and tracking tasks.","excerpt":"Graph-based RAG methods retrieve once from the entities a question names and so rarely recover the full evidence chain.","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"},{"text":"The authors report the best accuracy among thirteen baselines on three named datasets, using gpt-4o-mini and Qwen3.6 as backbones.","excerpt":"On MuSiQue, 2WikiMultiHopQA and HotpotQA, DeFT-RAG achieves the best accuracy among thirteen baselines with both gpt-4o-mini and Qwen3.6 as the backbone","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"},{"text":"With a QA cache shared across 1,000 MuSiQue questions, the authors report that 23.1% of sub-questions were answered from the cache and LLM calls fell by 12.9% without lower accuracy.","excerpt":"With a QA cache shared across 1,000 MuSiQue questions, 23.1% of sub-questions are answered from the cache, which reduces LLM calls by 12.9% without lowering accuracy.","url":"https://arxiv.org/abs/2610.37826","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2610.37826","checkedAt":"2026-11-08T00:16:06.523Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well does DeFT-RAG perform beyond the named benchmarks and cache conditions?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Kang and Li propose DeFT-RAG to break multi-hop questions into reusable steps","summary":"In their arXiv abstract, Dingyi Kang and Bingzhe Li propose DeFT-RAG, a retrieval-augmented generation (RAG) framework for multi-hop questions: questions that require combining facts spread across documents. They argue that graph-based RAG can miss the full evidence chain, while iterative RAG often asks the LLM to plan and manage too many steps.\n\nDeFT-RAG generates one self-contained sub-question at a time, using the original question and earlier question-answer pairs. A QA table tracks what has been answered; rule-based updates and a fine-tuned lightweight decision model handle work the authors say need not be done by the LLM. The framework also caches answers and reuses them when a later sub-question has the same meaning.\n\nThe authors report the best accuracy among thirteen baselines on MuSiQue, 2WikiMultiHopQA and HotpotQA with gpt-4o-mini and Qwen3.6, while using fewer input tokens than other iterative methods. In a test sharing a QA cache across 1,000 MuSiQue questions, 23.1% of sub-questions were answered from the cache, reducing LLM calls by 12.9% without lowering accuracy. These results concern the named datasets and model setups; the abstract does not establish performance on other tasks or in deployed systems. How well does DeFT-RAG perform beyond these benchmarks and cache conditions?","question":"How well does DeFT-RAG perform beyond the named benchmarks and cache conditions?","claims":[{"text":"Kang and Li propose DeFT-RAG, which generates self-contained sub-questions incrementally and reuses answers to address multi-hop questions.","excerpt":"We propose DeFT-RAG, a RAG framework built on three components.","support":"source-stated"},{"text":"The authors say graph-based RAG methods may miss the full evidence chain, while iterative RAG burdens the LLM with planning and tracking tasks.","excerpt":"Graph-based RAG methods retrieve once from the entities a question names and so rarely recover the full evidence chain.","support":"source-stated"},{"text":"The authors report the best accuracy among thirteen baselines on three named datasets, using gpt-4o-mini and Qwen3.6 as backbones.","excerpt":"On MuSiQue, 2WikiMultiHopQA and HotpotQA, DeFT-RAG achieves the best accuracy among thirteen baselines with both gpt-4o-mini and Qwen3.6 as the backbone","support":"source-stated"},{"text":"With a QA cache shared across 1,000 MuSiQue questions, the authors report that 23.1% of sub-questions were answered from the cache and LLM calls fell by 12.9% without lower accuracy.","excerpt":"With a QA cache shared across 1,000 MuSiQue questions, 23.1% of sub-questions are answered from the cache, which reduces LLM calls by 12.9% without lowering accuracy.","support":"source-stated"}],"limitations":["Evidence is the paper's arXiv abstract, not the full paper; it does not provide experimental details or results beyond the reported benchmarks and cache test.","The abstract does not establish how the reported results generalize to other datasets, model setups, or deployed systems."],"mediaId":"406f30760c8b39ebc737621233552582ec362f57f8b9b796e4ebf74827ef28a9","correctionReason":null,"id":"b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0","publicationId":"8f27d101-2f07-4890-8dfa-6c56cf8e0301","version":1,"sourceUrl":"https://arxiv.org/abs/2610.37826","sourceTitle":"DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-10-27","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-10-30T06:42:43.400Z","createdAt":"2026-11-08T00:01:11.162Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"406f30760c8b39ebc737621233552582ec362f57f8b9b796e4ebf74827ef28a9","kind":"article","url":"https://arxiv.org/abs/2610.37826","sourceUrl":"https://arxiv.org/abs/2610.37826","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-10-31T09:48:21.139Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2610.37826","checkedAt":"2026-11-08T00:16:06.523Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"406f30760c8b39ebc737621233552582ec362f57f8b9b796e4ebf74827ef28a9","confidence":0.8,"provider":"typesafe","model":"jev-1.13.0","inputHash":"286da027bda537eff1ca34f0a4d154dc4434e54db00603ff97828a122105dee6","decidedAt":"2026-10-31T09:48:22.821Z"},"provenance":{"textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observationId":"6b782356c781f12601956e8edbb913788963ce27eb5cff9685481e1ae3530170","retrievedAt":"2026-10-31T09:48:20.865Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"f81921ed-73de-4a79-8fb2-7766cc7c9584"},"reviewer":{"model":"gpt-6-luna","runId":"2a609297-ff0a-4391-897a-de43d5d8b9bd"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-08T00:01:11.162Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Kang, Dingyi","url":null,"kind":"unknown"},{"name":"Li, Bingzhe","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Kang, Dingyi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kang, Dingyi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.37826","locator":"head/meta[name=author|citation_author]"},"assertionId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-10-31T09:48:20.865Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd","sourceUrl":"https://arxiv.org/abs/2610.37826","contentSha256":"f434a6680cd7e3d405215c2b380dc8c36b2c020a6e98408edc919d31db31e032","textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observedAt":"2026-10-31T09:48:20.865Z"}},{"actor":{"name":"Li, Bingzhe","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Li, Bingzhe","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.37826","locator":"head/meta[name=author|citation_author]"},"assertionId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-10-31T09:48:20.865Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd","sourceUrl":"https://arxiv.org/abs/2610.37826","contentSha256":"f434a6680cd7e3d405215c2b380dc8c36b2c020a6e98408edc919d31db31e032","textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observedAt":"2026-10-31T09:48:20.865Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2610.37826","snapshotId":"3ae95c709ac166335d0deab2a702ae41072733b57c24b494deac4e1eca0269dd","contentSha256":"f434a6680cd7e3d405215c2b380dc8c36b2c020a6e98408edc919d31db31e032","textHash":"8e9039fe2ac5d0be74611adef6b3de67bc3beaf1df63c90e5e26263a5c956ecd","observedAt":"2026-10-31T09:48:20.865Z","basis":"publisher-page-metadata","sourceLinks":42,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/b879c3ddc1680410c28268854467a4d1ac90e754d40543d8058004945d0e2ca0/source"}}}],"audits":[{"publicationId":"8f27d101-2f07-4890-8dfa-6c56cf8e0301","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes DeFT-RAG and all reported results to the paper's listed authors, Dingyi Kang and Bingzhe Li. It frames performance figures as what the authors report, not as established fact.","excerpt":"Authors:Dingyi Kang, Bingzhe Li"},{"dimension":"summary","status":"uncertain","explanation":"The reading is faithful, but the central term RAG is named without saying what it does, and LLM is never expanded. A non-specialist cannot tell that RAG means an LLM answering by first retrieving passages from a corpus. Smallest repair: add the source's plain definition in the first sentence, and say that self-contained means each sub-question names every entity it asks about. Separately, the summary's closing sentence repeats the question field almost verbatim; that is redundant but minor.","excerpt":"Retrieval-augmented generation (RAG) lets a large language model (LLM) answer questions by retrieving relevant passages from a large corpus."},{"dimension":"date","status":"pass","explanation":"The originalPublished date of 2026-10-27 matches the v1 submission date. The later feed date of 2026-10-31 is correctly not used.","excerpt":"[Submitted on 27 Oct 2026]"},{"dimension":"support","status":"pass","explanation":"The claims about the method, the critique of graph-based and iterative RAG, the thirteen-baseline accuracy result, fewer input tokens, and the cache figures (23.1%, 12.9%) all match the abstract. The limitations and the question appropriately avoid stretching benchmark results into deployed reliability. The softening from 'rarely recover' to 'can miss' preserves the meaning.","excerpt":"giving the LLM fewer input tokens than any other iterative method"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page itself, the direct original source.","excerpt":null}],"createdAt":"2026-11-08T00:01:11.162Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}