{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/surface-based-retrieval-reduces-perplexity-of","title":"Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models","arxiv_id":"2305.16243","date":"2023-05-25","proceeding":null,"authors":["Ehsan Doostmohammadi","Tobias Norlund","Marco Kuhlmann","Richard Johansson"],"abstract":"Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval mechanism based on the similarity between dense representations of the query chunk and potential neighbors. In this paper, we study the state-of-the-art Retro model and observe that its performance gain is better explained by surface-level similarities, such as token overlap. Inspired by this, we replace the semantic retrieval in Retro with a surface-level method based on BM25, obtaining a significant reduction in perplexity. As full BM25 retrieval can be computationally costly for large datasets, we also apply it in a re-ranking scenario, gaining part of the perplexity reduction with minimal computational overhead.","url_abs":"https://arxiv.org/abs/2305.16243v3","url_pdf":"https://arxiv.org/pdf/2305.16243v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"surface-based-retrieval-reduces-perplexity-of","repo_url":"https://github.com/edoost/retro_bm25","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-retrieval","task_name":"Semantic Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.16243","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}