Papers › QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

15 Jun 2025arXiv:2506.12860archive 2025-07-28

Wanlong Liu, Junxiao Xu, Fei Yu, Yukang Lin, Ke Ji, Wenyu Chen, Yan Xu, Yasheng Wang, Lifeng Shang, Benyou Wang

Recent advancements in Long Chain-of-Thought (CoT) reasoning models have improved performance on complex tasks, but they suffer from overthinking, which generates redundant reasoning steps, especially for simple questions. This paper revisits the reasoning patterns of Long and Short CoT models, observing that the Short CoT patterns offer concise reasoning efficiently, while the Long CoT patterns excel in challenging scenarios where the Short CoT patterns struggle. To enable models to leverage both patterns, we propose Question-Free Fine-Tuning (QFFT), a fine-tuning approach that removes the input question during training and learns exclusively from Long CoT responses. This approach enables the model to adaptively employ both reasoning patterns: it prioritizes the Short CoT patterns and activates the Long CoT patterns only when necessary. Experiments on various mathematical datasets demonstrate that QFFT reduces average response length by more than 50%, while achieving performance comparable to Supervised Fine-Tuning (SFT). Additionally, QFFT exhibits superior performance compared to SFT in noisy, out-of-domain, and low-resource scenarios.

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 14 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 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: 14 samples from 1 repository, 14 ran (11 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lwl-cpu/question-free-fine-tuning officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 14 ran (3 instrument-failed) · 0 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

14 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 3 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 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
2ran · violated contract
3ran · our draft was wrong
8ran

Licence: 7 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 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 lwl-cpu/question-free-fine-tuning. “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.

lwl-cpu/question-free-fine-tuning official repository 14 samples, 14 ran (3 instrument-failed) · 0 unverified
check_sympy_equivalence eval/utils/math_normalization.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 33973ae45a70d4fe · report fixture: signature formatted_target_str:str/0/str, formatted_prediction_str:str/0/str · returned bool · level recorded 2026-09-24
choice_answer_clean in 17 papers eval/utils/grader.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 809c0178a7ae90ff · report fixture: signature pred:str/0/str · returned str · level recorded 2026-09-25
contains_wait eval/utils/analysis_difficulty.py ran Apache-2.0 (permissive) · b123cac6601e152a · report fixture: signature response:str/0/str · returned bool · level recorded 2026-09-25
extract_multi_choice_answer in 13 papers eval/utils/parser.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · ed2f4689128f9885 · report fixture: signature pred_str:str/0/str · returned str · level recorded 2026-09-25
extract_question in 7 papers eval/utils/analysis_difficulty.py ran fingerprinted Apache-2.0 (permissive) · 3bf1dc9721e95221 · report fixture: signature problem:str/0/str · returned str · level recorded 2026-09-25
get_conversation_prompt_by_messages eval/eval_tp.py ran Apache-2.0 (permissive) · 9c58d0990f07be11 · report fixture: signature tokenizer:MockTokenizer/0/?, messages:list/1/dict · returned str · level recorded 2026-09-25
get_three_prompt eval/eval_tp.py ran Apache-2.0 (permissive) · e458dae2ed344834 · report fixture: signature prompt_type:str/0/str, data_name:str/0/str · returned tuple · level recorded 2026-09-25
is_digit in 33 papers eval/utils/grader.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · fb37d3c84b18e368 · report fixture: signature num:str/0/str · returned bool · level recorded 2026-09-25
is_integer in 8 papers eval/utils/math_normalization.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · b804c6d0a0ddb922 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
load_math_test_levels eval/utils/analysis_difficulty.py ran Apache-2.0 (permissive) · 41c9b27031e839a7 · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
major_vote_accuracy eval/analysis/cal_all_cli.py ran Apache-2.0 (permissive) · 85f17e50933711f8 · report fixture: signature generated_answers:list/1/str, gold_answer:str/0/str, k:int/0/int, num_samples:int/0/int · returned float · level recorded 2026-09-25
normalize_final_answer in 20 papers eval/utils/math_normalization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 31ee6b861ee71ef7 · report fixture: signature final_answer:str/0/str · returned str · level recorded 2026-09-24
parse_digits in 20 papers eval/utils/grader.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 7d4b7f8c3875b126 · report fixture: signature num:str/0/str · returned float · level recorded 2026-09-25
parse_list in 10 papers eval/eval_tp.py ran fingerprinted Apache-2.0 (permissive) · c5b5032445c33c60 · report fixture: signature arg:str/0/str · returned list · level recorded 2026-09-25

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SFT

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