H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations

• URL: http://arxiv.org/abs/2605.00631v1
• Date: Fri, 01 May 2026 13:07:19 GMT
• Title: H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations
• Abstract summary: H-RAG addresses both Task A (Retrieval) and Task C (Generation with Retrieved Passages) in SemEval-2026 Task 8 (MTRAGEval)<n>Our approach implements a hierarchical parent-child RAG pipeline that separates fine-grained child-level retrieval from parent-level context reconstruction.<n>H-RAG achieves an nDCG@5 score of 0.4271 on Task A and a harmonic mean score of 0.3241 on Task C.
• Score: 6.221953137049602
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present H-RAG, our submission to SemEval-2026 Task 8 (MTRAGEval), addressing both Task A (Retrieval) and Task C (Generation with Retrieved Passages). Task A evaluates standalone retrieval quality, while Task C assesses end-to-end retrieval-augmented generation (RAG) in multi-turn conversational settings, requiring both accurate answer generation and faithful grounding in retrieved evidence. Our approach implements a hierarchical parent-child RAG pipeline that separates fine-grained child-level retrieval from parent-level context reconstruction during generation. Documents are segmented into overlapping sentence-based child chunks, while full documents are preserved as parent units to provide coherent context. Retrieval combines hybrid dense-sparse search, tunable weighting, and embedding-based similarity rescoring over child chunks. Retrieved evidence is aggregated at the parent level and supplied to an instruction-tuned language model for response generation. H-RAG achieves an nDCG@5 score of 0.4271 on Task A and a harmonic mean score of 0.3241 on Task C (RB_agg: 0.2488, RL_F: 0.2703, RB_llm: 0.6508), underscoring the importance of retrieval configuration and parent-level aggregation in multi-turn RAG performance.

Related papers

• VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval [65.89247522243959]
  VisDocAgentBench is a closed-corpus benchmark comparing static and agentic retrieval under a ranked-output contract.<n>It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures.<n>A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context.
  arXiv  Detail & Related papers  (2026-08-18T15:23:06Z)
• 5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control [0.0]
  We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval)<n>We evaluate multi-turn Retrieval Augmented Generation (RAG) systems.
  arXiv  Detail & Related papers  (2026-06-27T05:13:49Z)
• Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG [2.9721401411878254]
  Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits.<n>We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking.
  arXiv  Detail & Related papers  (2026-06-05T07:28:01Z)
• AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations [14.20669481486209]
  We present the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval)<n>We address all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-to-end RAG (C)<n>Our unified architecture is built on two principles: (i) a query-diversity-over-retriever-diversity strategy, and (ii) a multistage generation pipeline.
  arXiv  Detail & Related papers  (2026-03-11T08:28:31Z)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation [0.0]
  We introduce SPD-RAG, a hierarchical multi-agent framework for exhaustive cross-document question answering.<n>Each document is processed by a dedicated document-level agent operating only on its own content, enabling focused retrieval.<n>SPD-RAG achieves an Avg Score of 58.1 (GPT-5 evaluation), outperforming Normal RAG (33.0) and Agentic RAG (32.8) while using only 38% of the API cost of a full-context baseline (68.0)
  arXiv  Detail & Related papers  (2026-03-09T12:46:32Z)
• RAG-E: Quantifying Retriever-Generator Alignment and Failure Modes [10.900031381533354]
  RAG-E is an end-to-end explainability framework that quantifies retriever-generator alignment through mathematically grounded attribution methods.<n>We show that RAG output quality depends not solely on individual component performance but on their interplay, which can be audited via RAG-E.
  arXiv  Detail & Related papers  (2026-01-29T14:47:00Z)
• Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning [50.27838512822097]
  We introduce GlobalQA, the first benchmark specifically designed to evaluate global RAG capabilities.<n>We propose GlobalRAG, a multi-tool collaborative framework that preserves structural coherence through chunk-level retrieval.<n>On the Qwen2.5-14B model, GlobalRAG achieves 6.63 F1 compared to the strongest baseline's 1.51 F1.
  arXiv  Detail & Related papers  (2025-10-30T07:29:14Z)
• Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval [68.71038700559195]
  Chain of Retrieval(COR) is a novel iterative framework for full-paper retrieval.<n>We present SCIBENCH, a benchmark providing both complete and segmented contexts of full papers for queries and candidates.
  arXiv  Detail & Related papers  (2025-07-14T08:41:53Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• ImpRAG: Retrieval-Augmented Generation with Implicit Queries [34.72864597562907]
  ImpRAG is a query-free RAG system that integrates retrieval and generation into a unified model.<n>We show that ImpRAG achieves 3.6-11.5 improvements in exact match scores on unseen tasks with diverse formats.
  arXiv  Detail & Related papers  (2025-06-02T21:38:21Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)

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.