David Carmel
Research Subjects
David Carmel has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Oren Kurland
Technion, Haifa, Israel
5 shared publications - Yoelle Maarek
Technology Innovation Institute (TII), Haifa, Israel
3 shared publications - Guy Horowitz
Technology Innovation Institute (TII), Haifa, Israel
2 shared publications - Idan Pogrebinsky
Technion, Haifa, Israel
2 shared publications - Oren Somekh
Technology Innovation Institute (TII), Haifa, Israel
2 shared publications - Oz Huly
Technion, Haifa, Israel
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 897-908
Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 897-908
Open AccessPredicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3109-3116
LiveRAG: A Diverse Q&A Dataset with Varying Difficulty Level for RAG Evaluation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3109-3116
Open AccessLiveRAG: A Diverse Q&A Dataset with Varying Difficulty Level for RAG Evaluation
- Open Access
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 410-415
Enhancing Retrieval-Augmented Generation for Text Completion Through Query Selection
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 410-415
Open AccessEnhancing Retrieval-Augmented Generation for Text Completion Through Query Selection
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4199-4201
The LiveRAG Challenge at SIGIR 2025
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4199-4201
Open AccessThe LiveRAG Challenge at SIGIR 2025
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1283-1293
Predicting RAG Performance for Text Completion
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1283-1293
Open AccessPredicting RAG Performance for Text Completion
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2559-2563
Old IR Methods Meet RAG
Retrieval augmented generation (RAG) is an important approach to provide large language models (LLMs) with context pertaining to the text generation task: given a prompt, passages are retrieved from external corpora to ground the generation with more relevant and/or fresher data. Most previous studies used dense retrieval methods for applying RAG in question answering scenarios. However, recent work showed that traditional information retrieval methods (a.k.a. sparse methods) can do as well as or even better than dense retrieval ones. In particular, it was shown that Okapi BM25 outperforms dense retrieval methods, in terms of perplexity, for the fundamental text completion task in LLMs. We extend this study and show, using two popular LLMs, that a broad set of sparse retrieval methods achieve better results than all the dense retrieval methods we experimented with, for varying lengths of queries induced from the prompt. Furthermore, we found that Okapi BM25 is substantially outperformed by a term-proximity retrieval method (MRF), which is in turn outperformed by a pseudo-feedback-based bag-of-terms approach (relevance model). Additional exploration sheds some light on the effectiveness of lexical retrieval methods for RAG. Our findings call for further study of classical retrieval methods for RAG.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2559-2563
Open AccessOld IR Methods Meet RAG
Retrieval augmented generation (RAG) is an important approach to provide large language models (LLMs) with context pertaining to the text generation task: given a prompt, passages are retrieved from external corpora to ground the generation with more relevant and/or fresher data. Most previous studies used dense retrieval methods for applying RAG in question answering scenarios. However, recent work showed that traditional information retrieval methods (a.k.a. sparse methods) can do as well as or even better than dense retrieval ones. In particular, it was shown that Okapi BM25 outperforms dense retrieval methods, in terms of perplexity, for the fundamental text completion task in LLMs. We extend this study and show, using two popular LLMs, that a broad set of sparse retrieval methods achieve better results than all the dense retrieval methods we experimented with, for varying lengths of queries induced from the prompt. Furthermore, we found that Okapi BM25 is substantially outperformed by a term-proximity retrieval method (MRF), which is in turn outperformed by a pseudo-feedback-based bag-of-terms approach (relevance model). Additional exploration sheds some light on the effectiveness of lexical retrieval methods for RAG. Our findings call for further study of classical retrieval methods for RAG.
- Open Access
- 12 August 2012
- Published by Association for Computing Machinery (ACM)
- p. 1-6
A ranking framework for entity oriented search using Markov random fields
- 12 August 2012
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessA ranking framework for entity oriented search using Markov random fields
- Open Access
- 1 August 2008
- Published by Association for Computing Machinery (ACM) in Proceedings of the VLDB Endowment
- Vol. 1 (1) , 151-162
Maintaining dynamic channel profiles on the web
- 1 August 2008
- Published by Association for Computing Machinery (ACM) in Proceedings of the VLDB Endowment
- Vol. 1 (1) , 151-162
Open AccessMaintaining dynamic channel profiles on the web