aiqbench analysis
This research addresses a critical failure mode in retrieval-augmented generation (RAG) for multi-hop QA, where entity information is lost during query decomposition or sentence splitting. The authors propose Dual Entity Recovery RAG (DER-RAG), a lightweight method that maintains explicit grounding entities across the pipeline without requiring graph construction, corpus modification, or fine-tuning. By preserving context from retrieval through to generation, this approach effectively mitigates "lost-in-generation" errors and matches performance of more complex baselines.
Don't Lose Entities from Retrieval to Generation: Dual Entity Recovery RAG for multi-hop QA
arXiv:2609.06065v1 Announce Type: new Abstract: Retrieval-augmented multi-hop question answering (QA) decomposes a query into sub-questions and decomposes the corpus into smaller retrieval units such as sentences. Both forms of decomposition improve the pipeline, but we show that both share the same vulnerability, the loss of entity information, and that this loss breaks the pipeline at two separate points. The first point is retrieval, where a sub-question loses the entity resolved at the previous hop, leaving the retriever with nothing to match against. The second point is harder to see, because retrieval still appears to succeed. Once a passage is split into sentences, an isolated sentence loses the context that grounds its pronouns, so even with the correct sentence in hand the LLM cannot tell which entity the sentence is about. We isolate this second point as a distinct failure mode that we call lost-in-generation, and a retrieval-controlled experiment shows that it degrades answers even when the gold evidence is fixed in the context. We then propose Dual Entity Recovery RAG (DER-RAG), which keeps the grounding entity explicit from retrieval through to generation with two lightweight components, a two-way query decomposition that carries the resolved entity across sub-questions and a subject entity prefix attached to each sentence at generation time. DER-RAG needs no graph construction, no corpus modification, and no fine-tuning, yet on three multi-hop QA benchmarks it matches or exceeds strong baselines, including graph-based methods that depend on costly offline structures.
Abstract:Retrieval-augmented multi-hop question answering (QA) decomposes a query into sub-questions and decomposes the corpus into smaller retrieval units such as sentences. Both forms of decomposition improve the pipeline, but we show that both share the same vulnerability, the loss of entity information, and that this loss breaks the pipeline at two separate points. The first point is retrieval, where a sub-question loses the entity resolved at the previous hop, leaving the retriever with nothing to match against. The second point is harder to see, because retrieval still appears to succeed. Once a passage is split into sentences, an isolated sentence loses the context that grounds its pronouns, so even with the correct sentence in hand the LLM cannot tell which entity the sentence is about. We isolate this second point as a distinct failure mode that we call lost-in-generation, and a retrieval-controlled experiment shows that it degrades answers even when the gold evidence is fixed in the context. We then propose Dual Entity Recovery RAG (DER-RAG), which keeps the grounding entity explicit from retrieval through to generation with two lightweight components, a two-way query decomposition that carries the resolved entity across sub-questions and a subject entity prefix attached to each sentence at generation time. DER-RAG needs no graph construction, no corpus modification, and no fine-tuning, yet on three multi-hop QA benchmarks it matches or exceeds strong baselines, including graph-based methods that depend on costly offline structures.
Computation and Language (cs.CL)
arXiv:2609.06065 [cs.CL]
(or arXiv:2609.06065v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.06065 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 331 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow
arXiv · Jun 17, 2026
GraphRAG with TypeSafe Jev: A System One Approach to Scalable Knowledge Graphs
Towards Data Science · Sep 27, 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026