Papers › UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity...

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition

7 Aug 2023arXiv:2308.03279archive 2025-07-28

Wenxuan Zhou, Sheng Zhang, Yu Gu, Muhao Chen, Hoifung Poon

Large language models (LLMs) have demonstrated remarkable generalizability, such as understanding arbitrary entities and relations. Instruction tuning has proven effective for distilling LLMs into more cost-efficient models such as Alpaca and Vicuna. Yet such student models still trail the original LLMs by large margins in downstream applications. In this paper, we explore targeted distillation with mission-focused instruction tuning to train student models that can excel in a broad application class such as open information extraction. Using named entity recognition (NER) for case study, we show how ChatGPT can be distilled into much smaller UniversalNER models for open NER. For evaluation, we assemble the largest NER benchmark to date, comprising 43 datasets across 9 diverse domains such as biomedicine, programming, social media, law, finance. Without using any direct supervision, UniversalNER attains remarkable NER accuracy across tens of thousands of entity types, outperforming general instruction-tuned models such as Alpaca and Vicuna by over 30 absolute F1 points in average. With a tiny fraction of parameters, UniversalNER not only acquires ChatGPT's capability in recognizing arbitrary entity types, but also outperforms its NER accuracy by 7-9 absolute F1 points in average. Remarkably, UniversalNER even outperforms by a large margin state-of-the-art multi-task instruction-tuned systems such as InstructUIE, which uses supervised NER examples. We also conduct thorough ablation studies to assess the impact of various components in our distillation approach. We release the distillation recipe, data, and UniversalNER models to facilitate future research on targeted distillation.

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 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 1 repository, 8 ran (4 with no instrument failure; 4 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 8 samples that ran have no recorded date.

emma1066/retrieval-augmented-it-openner mentioned on GitHubpytorchSyntology: not harvested report
universal-ner/universal-ner mentioned on GitHubpytorchMITSyntology: 12 samples, 8 ran (4 instrument-failed) · 4 unverified 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: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 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 · violated contract
4ran · our draft was wrong
2ran
4unverified

Licence: 3 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from universal-ner/universal-ner. “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.

universal-ner/universal-ner community (archive-listed) 12 samples, 8 ran (4 instrument-failed) · 4 unverified
gen_prompt in 35 papers src/train/fastchat/eval/eval_gpt_review.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · a6a3ac30bf6e7bcf · report fixture: signature reviewer_jsons:list/1/dict, prompt_jsons:list/1/dict, cat:str/0/str, ques:str/0/str, ans1:str/0/str, ans2:str/0/str · returned tuple · level recorded 2026-09-22
get_response in 48 papers src/utils.py ran MIT (permissive) · fbd915d7d3d14137 · report fixture: signature responses:list/1/str · returned list · level recorded 2026-09-25
normalize_answer in 304 papers src/eval/evaluate.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e7e75981cb464788 · report fixture: signature s:str/0/str · returned str · level recorded, date not recorded
parse_score in 49 papers src/train/fastchat/eval/eval_gpt_review.py ran · violated contract fingerprinted MIT (permissive) · 8049b382893c73dd · report fixture: signature review:str/0/str · returned list · level recorded, date not recorded
parser in 5 papers src/eval/evaluate.py ran fingerprinted MIT (permissive) · 823ac03e72032fcb · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-24
read_jsonl in 136 papers src/train/fastchat/eval/generate_webpage_data_from_table.py ran · our draft was wrong MIT (permissive) · 7beeb01acc36919e · report fixture: signature path:str/0/str, key:str/0/str · returned dict · level recorded 2026-09-24
trim_hanging_lines src/train/fastchat/eval/generate_webpage_data_from_table.py ran · our draft was wrong fingerprinted MIT (permissive) · 1d45bc90fd0cd90c · report fixture: signature s:str/0/str, n:int/0/int · returned str · level recorded 2026-09-24
violates_moderation in 59 papers src/train/fastchat/utils.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · f9939a84b9a65279 · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-26
get_conv_template in 72 papers src/conversation.py unverified MIT (permissive) · dab937567e76e9e3 · report
get_eval in 18 papers src/train/fastchat/eval/eval_gpt_review.py unverified MIT (permissive) · 26ac62acef82f73c · report
get_gpu_memory in 16 papers src/train/fastchat/utils.py unverified MIT (permissive) · 2f3cb5d0dcc18502 · report
preprocess_instance src/utils.py unverified MIT (permissive) · 278f9963b50f1622 · report

Tasks

NERNamed Entity RecognitionNamed Entity Recognition (NER)Open Information Extractionnamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) ACE 2005 UniNER-7B F1 86.69 #8 of 20 Archive leaderboard report
Named Entity Recognition (NER) AnatEM UniNER-7B F1 88.65 #2 of 5 Archive leaderboard report
Named Entity Recognition (NER) BC2GM UniNER-7B F1 82.42 #13 of 13 Archive leaderboard report
Named Entity Recognition (NER) BC4CHEMD UniNER-7B F1 89.21 #7 of 7 Archive leaderboard report
Named Entity Recognition (NER) BC5CDR UniNER-7B F1 89.34 #10 of 16 Archive leaderboard report
Named Entity Recognition (NER) CoNLL03 UniNER-7B F1 93.3 #1 of 5 Archive leaderboard report
Named Entity Recognition (NER) FindVehicle UniNER-7B F1 98.3 #3 of 3 Archive leaderboard report
Named Entity Recognition (NER) GENIA UniNER-7B F1 77.54 #5 of 14 Archive leaderboard report
Named Entity Recognition (NER) NCBI Disease UniNER-7B F1 86.96 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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