DeFT‑RAG is a retrieval‑augmented generation framework that tackles multi‑hop questions by incrementally decomposing them into self‑contained sub‑questions. Each sub‑question explicitly names all entities it queries, eliminating the need for planning, dependency tracking, or rewriting, and allowing the LLM to focus on a single fine‑grained task. The system offloads bookkeeping to a rule‑based QA table and a lightweight decision model, caches answered QA pairs for reuse, and achieves state‑of‑the‑art accuracy on MuSiQue, 2WikiMultiHopQA, and HotpotQA while reducing LLM input tokens and calls.
By Dingyi Kang, Bingzhe Li
LatWeave is a deterministic multi‑hop question‑answering framework that structures knowledge into a multidimensional lattice and reduces QA to three operators—meet, compare, and abstain—while limiting LLM use to extraction and planning. It achieves near‑lossless performance on complete knowledge benchmarks (e.g., MetaQA) and strong results on templated multi‑hop datasets (e.g., 2WikiMultihopQA), while transparently handling incomplete knowledge through abstention. The approach offers reproducible, auditable answer paths with no performance penalty within its operating envelope.
By Yuze Ren, Shaoheng Fan, Tao Wang, Yabo Yan, Han Han
Hi-Q is a new framework for multi‑hop question answering that refines queries hierarchically based on evidence retrieved from a corpus. At each node it tests whether the current query unit is supported by evidence; if not, the node is expanded using a dependency‑preserving binary operator and verified for semantic coverage. The resulting query tree grows according to corpus support signals, and Hi‑Q achieves state‑of‑the‑art performance on three multi‑hop QA benchmarks, outperforming both iterative retrieval and graph‑based baselines without constructing a corpus‑wide graph.
By Jueun Kim, Sungho Park, Wook-Shin Han
The paper introduces EAR, an Entity‑Aware Partitioning approach that improves retrieval‑augmented generation for multiple‑choice question answering by extracting normalized surface anchors from questions, answers, and the corpus. EAR retrieves local windows around matching anchors and can attach a larger parent passage via an extractive summary, reducing retrieved words by 37.5‑40.2% compared to fixed‑size chunks. Experiments on a cleaned MMLU‑style subset with Mistral, Gemma, and DeepSeek show modest accuracy changes, none statistically significant, highlighting EAR’s methodological contribution of compact, inspectable retrieval units.
By Cenab Batu Bora, Oylum Alatl{\i}, Sebnem Bora, Oguz Dikenelli
arXiv:2608.21252v1 Announce Type: cross
Abstract: Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationshi...
By Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh, Jiawei Han
TriageRAG is a failure‑aware self‑training method for retrieval‑augmented language models that adapts them to specialized domains using only unlabeled text. It probes each self‑generated question with and without retrieved context, classifies the result into one of four categories (known, solved, context‑failure, retrieval‑failure), and routes each category to a tailored training signal, including a parametric route that teaches the reader to answer when retrieval misses. Experiments on 11 datasets across three domains and on CS‑Bench show that TriageRAG outperforms a budget‑matched SimRAG by 1.2–6.4 points and uniquely recovers closed‑book performance whenever retrieval harms the base model.
By Samarth Varshney, Ritu Yadav
The paper investigates why large language models (LLMs) miss evidence in multi‑hop retrieval‑augmented generation (RAG). It introduces ExecutionRAG, a training‑free register that tracks open sub‑questions and their supporting evidence, allowing the authors to distinguish between true retrieval failures and search drift. Using this method on 1,000 MuSiQue questions, the study shows a significant reduction in missed evidence but also reveals that other error types, such as premature resolutions and abstentions, increase, shifting the bottleneck from search guidance to evidence verification.
By Jiaqi Wei, Wenxuan Huang, Chengdong Xu, Xiang Zhang, Wanli Ouyang
The paper introduces ingest‑time fact compilation, an architecture that preprocesses and compiles corpus data into self‑contained facts with resolved revisions, deletions, and source trust. By storing this compiled state, query‑time models can retrieve answers directly, avoiding costly reconstruction from raw passages. Experiments show that this approach reduces read cost per question by 12.89× and token usage by 21.6× while maintaining accuracy.
By Kyle Wild, Yusuke Takahashi, Asako Uraki
arXiv:2608. 00585v1 Announce Type: cross Abstract: Verification for retrieval-augmented generation usually scores each retrieved chunk and drops the ones that fail.
By Randhir Kumar
arXiv:2606. 02488v1 Announce Type: new Abstract: Multi-hop question-answering systems often use expensive retrieval on every question.
By Yuyang Li, Zihe Yan, Tobias K\"afer
The paper introduces the concept of LLM‑specific utility, defining it as the performance gain a target large language model (LLM) achieves when provided with a passage compared to answering without evidence. A benchmark of utilitarian passages is built for four LLMs (Qwen3‑8B/14B/32B and Llama 3.1‑8B) across three QA datasets, revealing that each model benefits most from its own tailored evidence and that evidence optimized for other models is consistently suboptimal. The authors also create SpecUBench, a benchmark for LLM‑specific utility judgment, and show that current utility‑aware retrieval methods largely capture model‑agnostic usefulness, struggling to estimate LLM‑specific utility.
"whyItMatters":"The study demonstrates that retrieval‑augmented generation must consider model‑specific evidence selection to truly improve LLM performance, highlighting a gap in existing utility‑aware methods."
By Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
arXiv:2608. 04569v1 Announce Type: cross Abstract: Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget.
By Zhengpei Hu, Kai Li, Dapeng Fu, Xuechao Zou, Yuanhao Tang, Yue Li, Tengfei Cao, Jianqiang Huang