Papers › Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding...

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation

21 Feb 2024arXiv:2402.14874archive 2025-07-28

Phuc Phan, Hieu Tran, Long Phan

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur models or analysis of hidden state differences, DCD employs Contrastive Chain-of-thought Prompting and advanced distillation techniques, including Dropout and Quantization. This approach effectively addresses the limitations of Contrastive Decoding (CD), which typically requires both an expert and an amateur model, thus increasing computational resource demands. By integrating contrastive prompts with distillation, DCD obviates the need for an amateur model and reduces memory usage. Our evaluations demonstrate that DCD significantly enhances LLM performance across a range of reasoning benchmarks, surpassing both CD and existing methods in the GSM8K and StrategyQA datasets.

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 10 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 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: 10 samples from 1 repository, 6 ran (3 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

pphuc25/distil-cd officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 6 ran (3 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

10 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 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.

3ran · our draft was wrong
3ran
4unverified

Licence: 10 of the 10 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 pphuc25/distil-cd. “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.

pphuc25/distil-cd official repository 10 samples, 6 ran (3 instrument-failed) · 4 unverified
answer_cleansing dcd_eval/src/chorse/process_data.py ran no licence file found · pointer only · 8b5fd8ae1f77f932 · report fixture: signature args:Args/0/?, pred:str/0/str, question:str/0/str · returned str · level recorded 2026-09-24
create_regex_pattern dcd_eval/src/chorse/process_data.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b412890ab2fb1902 · report fixture: signature question:str/0/str · returned str · level recorded 2026-09-24
get_data_name_based_on_condition dcd_eval/src/chorse/process_data.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b452cd9127b6afcd · report fixture: signature prompt_file:str/0/str · returned str · level recorded 2026-09-24
is_correct in 12 papers dcd_eval/src/chorse/utils.py ran fingerprinted no licence file found · pointer only · 91b5a26d6a8fe4e5 · report fixture: signature model_answer:str/0/str, answer:str/0/str · returned bool · level recorded 2026-09-24
load_json in 344 papers dcd_eval/src/compute_accuracy.py ran · our draft was wrong no licence file found · pointer only · 593e5e4d03d4d4df · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-22
set_stop_words src/dcd/utils.py ran no licence file found · pointer only · 7e57dc83814a2145 · report fixture: signature tokenizer:MinimalTokenizer/0/?, stop_words:list/1/str · returned StoppingCriteriaList · level recorded 2026-09-24
create_prompt in 50 papers src/dcd/prompts.py unverified no licence file found · pointer only · 8e4e00b93dabaf41 · report
create_prompt_student src/dcd/prompts.py unverified no licence file found · pointer only · 80618aec403147a1 · report
get_model_master_and_amateur dcd_eval/src/chorse/load_model.py unverified no licence file found · pointer only · d7b3ad79f1f8bd95 · report
greedy_search in 7 papers src/dcd/generate.py unverified no licence file found · pointer only · ad7789fd83efa143 · report

Tasks

Arithmetic ReasoningGSM8KLanguage ModellingQuantizationStrategyQA

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dropout

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