Papers › Intent Factored Generation: Unleashing the Diversity in Your Language Model

Intent Factored Generation: Unleashing the Diversity in Your Language Model

11 Jun 2025arXiv:2506.09659archive 2025-07-28

Eltayeb Ahmed, Uljad Berdica, Martha Elliott, Danijela Horak, Jakob N. Foerster

Obtaining multiple meaningfully diverse, high quality samples from Large Language Models for a fixed prompt remains an open challenge. Current methods for increasing diversity often only operate at the token-level, paraphrasing the same response. This is problematic because it leads to poor exploration on reasoning problems and to unengaging, repetitive conversational agents. To address this we propose Intent Factored Generation (IFG), factorising the sampling process into two stages. First, we sample a semantically dense intent, e.g., a summary or keywords. Second, we sample the final response conditioning on both the original prompt and the intent from the first stage. This allows us to use a higher temperature during the intent step to promote conceptual diversity, and a lower temperature during the final generation to ensure the outputs are coherent and self-consistent. Additionally, we find that prompting the model to explicitly state its intent for each step of the chain-of-thought before generating the step is beneficial for reasoning tasks. We demonstrate our method's effectiveness across a diverse set of tasks. We show this method improves both pass@k and Reinforcement Learning from Verifier Feedback on maths and code tasks. For instruction-tuning, we combine IFG with Direct Preference Optimisation to increase conversational diversity without sacrificing reward. Finally, we achieve higher diversity while maintaining the quality of generations on a general language modelling task, using a new dataset of reader comments and news articles that we collect and open-source. In summary, we present a simple method of increasing the sample diversity of LLMs while maintaining performance. This method can be implemented by changing the prompt and varying the temperature during generation, making it easy to integrate into many algorithms for gains across various applications.

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: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

flairox/ifg officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (0 instrument-failed) · 1 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: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

11ran
1unverified

Licence: 0 of the 12 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 flairox/ifg. “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.

flairox/ifg official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
compare_final_answer_to_ground_truth hendrycks_math/math_eval.py ran fingerprinted Apache-2.0 (permissive) · e6b10b3a46a1e73c · report fixture: signature generation:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-25
compute_performance_metrics hendrycks_math/ifg_infer_and_score.py ran Apache-2.0 (permissive) · 25929c22eda9938b · report fixture: signature attempted_problems:list/1/EvaluatedProblem, num_attempts:int/0/int, verbose:bool/0/bool · returned tuple · level recorded 2026-09-25
create_dataset_of_size_batch_size training/tune_batch_size.py ran Apache-2.0 (permissive) · b881ac314109956a · report fixture: signature input_dataset_path:str/0/str, output_dataset_path:str/0/str, batch_size:int/0/int · returned str · level recorded 2026-09-25
format_duration in 11 papers hendrycks_math/experiment_pipelines/hparam_sweeper.py ran fingerprinted Apache-2.0 (permissive) · 606bde9343246a50 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-25
generate_subpaths hendrycks_math/star.py ran fingerprinted Apache-2.0 (permissive) · 79035c5cd6888332 · report fixture: signature base_dir:str/0/str, iteration:int/0/int · returned dict · level recorded 2026-09-25
get_bound hendrycks_math/experiment_pipelines/hparam_sweeper.py ran Apache-2.0 (permissive) · b99c690a18bac742 · report fixture: signature min_bound:float/0/float, max_bound:float/0/float, mode:str/0/str · returned tuple · level recorded 2026-09-25
get_result in 30 papers hendrycks_math/experiment_pipelines/hparam_sweeper.py ran Apache-2.0 (permissive) · adc1130833a4f725 · report fixture: signature results_file_path:str/0/str, metric:str/0/str · returned float · level recorded 2026-09-25
preprocess_sample training/finetune_completion.py ran Apache-2.0 (permissive) · e15df122cc85e5a6 · report fixture: signature sample:dict/0/?, tokenizer:callable/0/?, separator:str/0/str, add_explicit_eos_token:bool/0/bool · returned dict · level recorded 2026-09-25
process_docs hendrycks_math/math_eval.py ran Apache-2.0 (permissive) · 1ab57d52c0087750 · report fixture: signature dataset:Dataset/0/? · returned Dataset · level recorded 2026-09-25
process_results in 11 papers hendrycks_math/math_eval.py ran Apache-2.0 (permissive) · 90f8729aba04c979 · report fixture: signature doc:dict/0/?, results:list/1/str · returned dict · level recorded 2026-09-25
read_prompt_file training/finetune_completion.py ran Apache-2.0 (permissive) · 196f3f69c8d074dd · report fixture: signature file_path:str/0/str · returned str · level recorded 2026-09-25
evaluate_comments unstructured_tasks/metrics/reward_model_eval.py unverified Apache-2.0 (permissive) · e213f105ef5bfbfa · report

Tasks

ArticlesDiversityLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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