STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA

• URL: http://arxiv.org/abs/2607.10795v1
• Date: Sun, 12 Jul 2026 15:06:11 GMT
• Title: STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA
• Abstract summary: We propose STEC, an evidence compression framework for final answer selection in multi-hop QA.<n>STEC selects the final answer from the existing candidate set through two mechanisms.<n>We evaluate STEC on four open-domain multi-hop QA benchmarks against representative baselines.
• Score: 25.230092433110766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing methods mainly improve open-domain multi-hop QA through reasoning paradigms, retrieval interaction, and search strategy optimization. However, using multiple search trajectories introduces a challenging final answer selection problem. Different trajectories may support different candidates, and the retrieved information can be heterogeneous, redundant, incomplete, or conflicting. Directly comparing raw trajectories exposes the verifier to noisy and unaligned content, while comparing answer strings ignores the evidence supporting each candidate, making reliable final selection difficult. To address this challenge, we propose STEC, an evidence compression framework for final answer selection in multi-hop QA. STEC selects the final answer from the existing candidate set through two mechanisms: (1) Answer-Level Evidence Compression, which groups trajectories by normalized answer identity and converts each answer group into a candidate-specific evidence representation; and (2) Evidence-Guided Answer Verification, which compares these representations and selects the final answer from the candidate set. The design shifts final selection from raw trajectory comparison to candidate-level evidence comparison. We evaluate STEC on four open-domain multi-hop QA benchmarks against representative baselines. Experimental results show that STEC performs best overall among the compared methods, and ablation results provide evidence that answer-level evidence compression contributes to final answer selection.

Related papers

• Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval [19.37201042661162]
  We propose a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking.<n> Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in retrieval quality and downstream QA performance over baselines.
  arXiv  Detail & Related papers  (2026-09-07T05:13:56Z)
• Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering [5.690260503175008]
  Knowledge graph question answering (KGQA) aims to answer natural-language questions by reasoning over structured facts.<n>Existing multi-hop KGQA methods mainly rely on topic-centered expansion, which faces two key challenges.<n>We propose OPI, an ontology-guided evidence path inference framework for multi-hop KGQA.
  arXiv  Detail & Related papers  (2026-06-26T13:40:51Z)
• CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency [9.50454647525075]
  We introduce CQC-RAG, a framework that co-designs query-level diversity injection with cross-Query Consistency evaluation.<n>CQC-RAG rewrites the original question into diverse but meaning-preserving queries.<n>It applies an evidence-grounded protocol to extract answer-evidence pairs and selects answers according to confidence stability.
  arXiv  Detail & Related papers  (2026-06-11T15:01:49Z)
• Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends [16.699029984948073]
  This survey takes the execution procedure as the unit of analysis and introduces a four-axis framework.<n>We map representative multi-hop QA systems and synthesize reported ablations and tendencies on standard benchmarks.<n>We conclude with open challenges for retrieval--reasoning agents, including structure-aware planning, transferable control policies, and robust stopping under distribution shift.
  arXiv  Detail & Related papers  (2026-01-02T02:38:01Z)
• Diverse Multi-Answer Retrieval with Determinantal Point Processes [11.925050407713597]
  We propose a re-ranking based approach using Determinantal point processes utilizing BERT as kernels. Results demonstrate that our re-ranking technique outperforms state-of-the-art method on the AmbigQA dataset.
  arXiv  Detail & Related papers  (2022-11-29T08:54:05Z)
• Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge [82.5582220249183]
  We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources. Unlike previous methods that solely rely on the retriever for gathering all evidence in isolation, our intermediary performs a chain of reasoning over the retrieved set. Our system achieves competitive performance on two ODQA datasets, OTT-QA and NQ, against tables and passages from Wikipedia.
  arXiv  Detail & Related papers  (2022-10-22T03:21:32Z)
• Modeling Multi-hop Question Answering as Single Sequence Prediction [88.72621430714985]
  We propose a simple generative approach (PathFid) that extends the task beyond just answer generation. PathFid explicitly models the reasoning process to resolve the answer for multi-hop questions. Our experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets.
  arXiv  Detail & Related papers  (2022-05-18T21:57:59Z)
• Double Retrieval and Ranking for Accurate Question Answering [120.69820139008138]
  We show that an answer verification step introduced in Transformer-based answer selection models can significantly improve the state of the art in Question Answering. The results on three well-known datasets for AS2 show consistent and significant improvement of the state of the art.
  arXiv  Detail & Related papers  (2022-01-16T06:20:07Z)
• Adaptive Information Seeking for Open-Domain Question Answering [61.39330982757494]
  We propose a novel adaptive information-seeking strategy for open-domain question answering, namely AISO. According to the learned policy, AISO could adaptively select a proper retrieval action to seek the missing evidence at each step. AISO outperforms all baseline methods with predefined strategies in terms of both retrieval and answer evaluations.
  arXiv  Detail & Related papers  (2021-09-14T15:08:13Z)
• Answering Any-hop Open-domain Questions with Iterative Document Reranking [62.76025579681472]
  We propose a unified QA framework to answer any-hop open-domain questions. Our method consistently achieves performance comparable to or better than the state-of-the-art on both single-hop and multi-hop open-domain QA datasets.
  arXiv  Detail & Related papers  (2020-09-16T04:31:38Z)
• Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games [66.98855910291292]
  We propose a new problem of learning to recover reasoning chains from weakly supervised signals. How the evidence passages are selected and how the selected passages are connected are handled by two models. For evaluation, we created benchmarks based on two multi-hop QA datasets.
  arXiv  Detail & Related papers  (2020-04-06T03:54:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.