H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913080581029888 |
|---|---|
| author | Elchafei, Passant Emam, Hossam Alansary, Mohamed Swain, Monorama Schedl, Markus |
| author_facet | Elchafei, Passant Emam, Hossam Alansary, Mohamed Swain, Monorama Schedl, Markus |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00631 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations Elchafei, Passant Emam, Hossam Alansary, Mohamed Swain, Monorama Schedl, Markus Computation and Language Information Retrieval 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. |
| title | H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2605.00631 |