Papers › D2PO: Discriminator-Guided DPO with Response Evaluation Models

D2PO: Discriminator-Guided DPO with Response Evaluation Models

2 May 2024arXiv:2405.01511archive 2025-07-28

Prasann Singhal, Nathan Lambert, Scott Niekum, Tanya Goyal, Greg Durrett

Varied approaches for aligning language models have been proposed, including supervised fine-tuning, RLHF, and direct optimization methods such as DPO. Although DPO has rapidly gained popularity due to its straightforward training process and competitive results, there is an open question of whether there remain practical advantages of using a discriminator, like a reward model, to evaluate responses. We propose D2PO, discriminator-guided DPO, an approach for the online setting where preferences are being collected throughout learning. As we collect gold preferences, we use these not only to train our policy, but to train a discriminative response evaluation model to silver-label even more synthetic data for policy training. We explore this approach across a set of diverse tasks, including a realistic chat setting, we find that our approach leads to higher-quality outputs compared to DPO with the same data budget, and greater efficiency in terms of preference data requirements. Furthermore, we show conditions under which silver labeling is most helpful: it is most effective when training the policy with DPO, outperforming traditional PPO, and benefits from maintaining a separate discriminator from the policy model.

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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

PrasannS/d2po officialmentioned in paperpytorchSyntology: 13 samples, 11 ran (3 instrument-failed) · 2 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
3ran · our draft was wrong
7ran
2unverified

Licence: 13 of the 13 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 PrasannS/d2po. “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.

PrasannS/d2po official repository 13 samples, 11 ran (3 instrument-failed) · 2 unverified
add_row_index src/train_rm.py ran no licence file found · pointer only · bdf1e0f893679196 · report fixture: signature example:dict/0/?, idx:int/0/int · returned dict · level recorded 2026-09-24
adjust_input src/eval/generate_outs.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 39dae513044dc499 · report fixture: signature strval:str/0/str, apf:bool/0/bool · returned str · level recorded 2026-09-24
adjust_tulu src/eval/generate_outs.py ran fingerprinted no licence file found · pointer only · 22de807813131078 · report fixture: signature question:str/0/str, useless:NoneType/0/? · returned str · level recorded 2026-09-24
get_step_ckpt src/eval/generate_outs.py ran no licence file found · pointer only · af95fc70de192cc3 · report fixture: signature ckpt:str/0/str, origmodel:callable/0/? · returned DummyModel · level recorded 2026-09-24
lensco src/utils/rl_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · ea8d7cf234eea3bb · report fixture: signature lval:float/0/float · returned float · level recorded 2026-09-24
new_forward rlhfutils/rlhfutils/modeling_override.py ran no licence file found · pointer only · d0004fe553444d0e · report fixture: signature self:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/int, head_mask:NoneType/0/?, past_key_values:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:Tensor/2/int, use_cache:bool/0/bool, output_attentions:bool/0/bool, output_hidden_states:bool/0/bool, return_dict:bool/0/bool, seq_loss:bool/0/bool · returned CausalLMOutputWithPast · level recorded 2026-09-24
onlyans src/train_dpo.py ran no licence file found · pointer only · 80a8b3f87c775a21 · report fixture: signature _:NoneType/0/?, answer:str/0/str · returned str · level recorded 2026-09-24
prepare_sample_text in 10 papers src/trainsft.py ran · our draft was wrong no licence file found · pointer only · 148dc2c38b7cd922 · report fixture: signature example:dict/0/? · returned str · level recorded 2026-09-24
preproc_wgpt src/eval/generate_outs_old.py ran · our draft was wrong no licence file found · pointer only · 3f0252eb62a38d86 · report fixture: signature example:dict/0/? · returned dict · level recorded 2026-09-24
simplecat src/train_dpo.py ran fingerprinted no licence file found · pointer only · b4cda67a5a5317e9 · report fixture: signature question:str/0/str, answer:str/0/str · returned str · level recorded 2026-09-24
tulu_pf src/train_dpo.py ran fingerprinted no licence file found · pointer only · ab9274275c75ba41 · report fixture: signature question:str/0/str, answer:str/0/str · returned str · level recorded 2026-09-24
get_pipeline in 5 papers src/utils/rl_utils.py unverified no licence file found · pointer only · 576b5052f87d577b · report
load_stack src/eval/generate_outs_old.py unverified no licence file found · pointer only · 8faae6d33f36ed52 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DPOEntropy RegularizationPPOSET

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