Papers › OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

21 Nov 2024arXiv:2411.14199archive 2025-07-28

Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D'Arcy, David Wadden, Matt Latzke, Minyang Tian, Pan Ji, Shengyan Liu, Hao Tong, Bohao Wu, Yanyu Xiong, Luke Zettlemoyer, Graham Neubig, Dan Weld, Doug Downey, Wen-tau Yih, Pang Wei Koh, Hannaneh Hajishirzi

Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscience, and biomedicine. On ScholarQABench, OpenScholar-8B outperforms GPT-4o by 5% and PaperQA2 by 7% in correctness, despite being a smaller, open model. While GPT4o hallucinates citations 78 to 90% of the time, OpenScholar achieves citation accuracy on par with human experts. OpenScholar's datastore, retriever, and self-feedback inference loop also improves off-the-shelf LMs: for instance, OpenScholar-GPT4o improves GPT-4o's correctness by 12%. In human evaluations, experts preferred OpenScholar-8B and OpenScholar-GPT4o responses over expert-written ones 51% and 70% of the time, respectively, compared to GPT4o's 32%. We open-source all of our code, models, datastore, data and a public demo.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 2 repositories, 9 ran (4 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

akariasai/openscholar officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
akariasai/openscholar_experteval officialmentioned in paperSyntology: 8 samples, 5 ran (2 instrument-failed) · 3 unverified report
akariasai/scholarbench officialmentioned in paperpytorchMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
1ran
3unverified

Licence: 8 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

akariasai/openscholar official repository 4 samples, 4 ran (3 instrument-failed) · 0 unverified
calculate_openai_api_cost src/open_scholar.py ran · honoured contract Apache-2.0 (permissive) · ebcbc14c5f0a26eb · report fixture: signature input_tokens:int/0/int, output_tokens:int/0/int, model_name:str/0/str · returned float · level recorded 2026-09-22
get_passage_pos_ids retriever/api/passage_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 2254a963dae027e0 · report fixture: signature passage_dir:str/0/str, pos_map_save_path:str/0/str · returned dict · level recorded 2026-09-22
remove_citations in 8 papers src/open_scholar.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5df8b525aada9853 · report fixture: signature sent:str/0/str · returned str · level recorded 2026-09-22
rerank_paragraphs_bge src/open_scholar.py ran · our draft was wrong Apache-2.0 (permissive) · 9fcb6754cab0d0dd · report fixture: signature query:str/0/str, paragraphs:list/1/dict, reranker:callable/0/?, norm_cite:bool/0/bool, start_index:int/0/int, use_abstract:bool/0/bool · returned tuple · level recorded 2026-09-22
akariasai/openscholar_experteval official repository 8 samples, 5 ran (2 instrument-failed) · 3 unverified
calculate_avg_fine_grained_scores compute_metrics.py ran · honoured contract no licence file found · pointer only · 0c17dfce015ab2fe · report fixture: signature results:dict/0/?, aspect:str/0/str · returned float64 · level recorded 2026-09-25
get_finegrained_results compute_metrics.py ran no licence file found · pointer only · e09711ced33247ae · report fixture: signature records:list/1/Record, target_model_a:str/0/str, target_model_b:str/0/str, aspects:list/1/str · returned dict · level recorded 2026-09-25
is_integer_string use_search_apis.py ran · violated contract no licence file found · pointer only · 4419dd4c768a4bb5 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-22
normalize_citations convert_output_files.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3ae3bb73bff5368f · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
remove_citations in 8 papers convert_output_files.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5fd3281e2c36928f · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
get_acceptance_results compute_metrics.py unverified no licence file found · pointer only · 8c75664adcd9b212 · report
get_paper_data use_search_apis.py unverified no licence file found · pointer only · f4d87e94b7582645 · report
search_paper_via_title use_search_apis.py unverified no licence file found · pointer only · b6c21051ff3f26c8 · report

Tasks

Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections