Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.11832 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913614255882240 |
|---|---|
| author | Che, Tian-Yi Mao, Xian-Ling Xu, Chun Xin, Cheng-Xin Xu, Heng-Da Liu, Jin-Yu Huang, Heyan |
| author_facet | Che, Tian-Yi Mao, Xian-Ling Xu, Chun Xin, Cheng-Xin Xu, Heng-Da Liu, Jin-Yu Huang, Heyan |
| contents | Numerous retrieval models, including sparse, dense and llm-based methods, have demonstrated remarkable performance in predicting the relevance between queries and corpora. However, the preliminary effectiveness analysis experiments indicate that these models fail to achieve satisfactory performance on the majority of queries and corpora, revealing their effectiveness restricted to specific scenarios. Thus, to tackle this problem, we propose a novel Distributed Collaborative Retrieval Framework (DCRF), outperforming each single model across all queries and corpora. Specifically, the framework integrates various retrieval models into a unified system and dynamically selects the optimal results for each user's query. It can easily aggregate any retrieval model and expand to any application scenarios, illustrating its flexibility and scalability.Moreover, to reduce maintenance and training costs, we design four effective prompting strategies with large language models (LLMs) to evaluate the quality of ranks without reliance of labeled data. Extensive experiments demonstrate that proposed framework, combined with 8 efficient retrieval models, can achieve performance comparable to effective listwise methods like RankGPT and ListT5, while offering superior efficiency. Besides, DCRF surpasses all selected retrieval models on the most datasets, indicating the effectiveness of our prompting strategies on rank-oriented automatic evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11832 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Distributed Collaborative Retrieval Framework Excelling in All Queries and Corpora based on Zero-shot Rank-Oriented Automatic Evaluation Che, Tian-Yi Mao, Xian-Ling Xu, Chun Xin, Cheng-Xin Xu, Heng-Da Liu, Jin-Yu Huang, Heyan Information Retrieval Numerous retrieval models, including sparse, dense and llm-based methods, have demonstrated remarkable performance in predicting the relevance between queries and corpora. However, the preliminary effectiveness analysis experiments indicate that these models fail to achieve satisfactory performance on the majority of queries and corpora, revealing their effectiveness restricted to specific scenarios. Thus, to tackle this problem, we propose a novel Distributed Collaborative Retrieval Framework (DCRF), outperforming each single model across all queries and corpora. Specifically, the framework integrates various retrieval models into a unified system and dynamically selects the optimal results for each user's query. It can easily aggregate any retrieval model and expand to any application scenarios, illustrating its flexibility and scalability.Moreover, to reduce maintenance and training costs, we design four effective prompting strategies with large language models (LLMs) to evaluate the quality of ranks without reliance of labeled data. Extensive experiments demonstrate that proposed framework, combined with 8 efficient retrieval models, can achieve performance comparable to effective listwise methods like RankGPT and ListT5, while offering superior efficiency. Besides, DCRF surpasses all selected retrieval models on the most datasets, indicating the effectiveness of our prompting strategies on rank-oriented automatic evaluation. |
| title | A Distributed Collaborative Retrieval Framework Excelling in All Queries and Corpora based on Zero-shot Rank-Oriented Automatic Evaluation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2412.11832 |