Papers › Training language models to follow instructions with human feedback

Training language models to follow instructions with human feedback

4 Mar 2022arXiv:2203.02155archive 2025-07-28

Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe

Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these models are not aligned with their users. In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback. Starting with a set of labeler-written prompts and prompts submitted through the OpenAI API, we collect a dataset of labeler demonstrations of the desired model behavior, which we use to fine-tune GPT-3 using supervised learning. We then collect a dataset of rankings of model outputs, which we use to further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT. In human evaluations on our prompt distribution, outputs from the 1.3B parameter InstructGPT model are preferred to outputs from the 175B GPT-3, despite having 100x fewer parameters. Moreover, InstructGPT models show improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets. Even though InstructGPT still makes simple mistakes, our results show that fine-tuning with human feedback is a promising direction for aligning language models with human intent.

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

The archive's official repository (openai/following-instructions-human-feedback) was not harvested; the 4 samples below come from 1 community repository.

Syntology 4 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 4 samples from 1 repository, 4 ran (4 with no instrument failure; 0 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.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

openai/following-instructions-human-feedback officialmentioned in paperSyntology: not harvested report
daniel-furman/sft-demos mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to QLoRA: Efficient Finetuning of Quantized LLMs (arXiv:2305.14314; that paper's own run record: 18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
ggerganov/llama.cpp mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration (arXiv:2306.00978; that paper's own run record: 16 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ggml-org/llama.cpp mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Composable Evaluation System for Reproducible Omni-Modal Foundation Model Evaluation (arXiv:2609.01315; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
grantslatton/llama.cpp mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LLaMA: Open and Efficient Foundation Language Models (arXiv:2302.13971; that paper's own run record: 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified); nothing checks that they implement this paper's method. report
hiyouga/llama-efficient-tuning mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large Language Models for Cyber Security: A Systematic Literature Review (arXiv:2405.04760; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
laion-ai/open-assistant mentioned on GitHubApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
longhao-chen/aicas2024 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LLaMA: Open and Efficient Foundation Language Models (arXiv:2302.13971; that paper's own run record: 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified); nothing checks that they implement this paper's method. report
tatsu-lab/alpaca_farm mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment (arXiv:2501.09620; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
tatsu-lab/linguistic_calibration mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation (arXiv:2305.14251; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 3 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
openrlhf/openrlhf pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Regret Minimization Framework on Preference Learning in Large Language Models (arXiv:2606.09124; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

4ran

Licence: 0 of the 4 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 laion-ai/open-assistant. “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.

laion-ai/open-assistant community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
batch_inference model/model_eval/eval_rm.py ran Apache-2.0 (permissive) · cf5703983b5310d1 · report fixture: signature inputs:tuple/1/dict, model:callable/0/? · returned EvalPrediction · level recorded 2026-09-24
batch_inference model/model_eval/sampling_score.py ran Apache-2.0 (permissive) · 45981d36c1069760 · report fixture: signature model:callable/0/?, dataloader:list/1/dict · returned tuple · level recorded 2026-09-24
describe_samples model/model_eval/utils.py ran Apache-2.0 (permissive) · b43436c7df4225f4 · report fixture: signature samples:list/1/dict · returned dict · level recorded 2026-09-24
load_sampling_data model/model_eval/utils.py ran Apache-2.0 (permissive) · 8825793b366ca162 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24

Tasks

Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering TIQ InstructGpt P@1 23.6 #6 of 9 Archive leaderboard report
Question Answering TimeQuestions InstructGPT P@1 22.4 #19 of 21 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.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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