paper-with-me

홈 › Papers

Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking

2026-05-12 · David-Maximilian Caraman, Gheorghe Cosmin Silaghi arxiv

We describe our system for SemEval-2026 Task 8 (MTRAGEval), participating in Task A (Retrieval) across four English-language domains. Our approach employs a three-stage pipeline: (1) query rewriting via a LoRA-fine-tuned Qwen 2.5 7B model that transforms context-dependent follow-up questions into standalone queries, (2) hybrid BM25 and dense retrieval combined through Reciprocal Rank Fusion, and (3) cross-encoder reranking with BGE-reranker-v2-m3. On the official test set, the system achieves nDCG@5 of 0.531, ranking 8th out of 38 participating systems and 10.7% above the organizer baseline. Development comparisons reveal that domain-specific temperature tuning for query generation, where technical domains benefit from deterministic decoding and general domains from controlled randomness, provides consistent gains, while more complex strategies such as domain-aware prompting and multi-query expansion degrade performance.

📄 PDF Abstract BibTeX arXiv:2605.12028

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

KGP at SemEval-2021 Task 8: Leveraging Multi-Staged Language Models for Extracting Measurements, their Attributes and Relations

2021-08-01 · SEMEVAL 2021 · Neel Karia, Ayush Kaushal, Faraaz Mallick

SemEval-2021 Task 8: MeasEval aims at improving the machine understanding of measurements in scientific texts through a set of entity and semantic relation extraction sub-tasks on identifying quantity spans along with va…

Multi-Task LearningRelation Extraction

AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning

2026-03-04 · Nikolas Karafyllis, Maria Lymperaiou, Giorgos Filandrianos, Athanasios Voulodimos 외 arxiv

We present a winning three-stage system for SemEval 2026 Task~12: Abductive Event Reasoning that combines graph-based retrieval, LLM-driven abductive reasoning with prompt design optimized through reflective prompt evolu…

LingJing at SemEval-2022 Task 1: Multi-task Self-supervised Pre-training for Multilingual Reverse Dictionary

2022-07-01 · SemEval (NAACL) 2022 7 · Bin Li, Yixuan Weng, Fei Xia, Shizhu He 외

This paper introduces the approach of Team LingJing’s experiments on SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings (CODWOE). This task aims at comparing two types of semantic descriptions and including t…

Reverse DictionaryWord Embeddings

IHS-RD-Belarus at SemEval-2016 Task 1: Multistage Approach for Measuring Semantic Similarity

2016-06-01 · SEMEVAL 2016 6 · Maryna Beliuha, Maryna Chernyshevich
Information RetrievalMachine TranslationQuestion AnsweringSemantic Similarity+2

AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations

2026-03-11 · Dimosthenis Athanasiou, Maria Lymperaiou, Giorgos Filandrianos, Athanasios Voulodimos 외 arxiv

We present the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval), addressing all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-…

Response GenerationPassage Retrieval