Papers › Suri: Multi-constraint Instruction Following for Long-form Text Generation

Suri: Multi-constraint Instruction Following for Long-form Text Generation

27 Jun 2024arXiv:2406.19371archive 2025-07-28

Chau Minh Pham, Simeng Sun, Mohit Iyyer

Existing research on instruction following largely focuses on tasks with simple instructions and short responses. In this work, we explore multi-constraint instruction following for generating long-form text. We create Suri, a dataset with 20K human-written long-form texts paired with LLM-generated backtranslated instructions that contain multiple complex constraints. Because of prohibitive challenges associated with collecting human preference judgments on long-form texts, preference-tuning algorithms such as DPO are infeasible in our setting; thus, we propose Instructional ORPO (I-ORPO), an alignment method based on the ORPO algorithm. Instead of receiving negative feedback from dispreferred responses, I-ORPO obtains negative feedback from synthetically corrupted instructions generated by an LLM. Using Suri, we perform supervised and I-ORPO fine-tuning on Mistral-7b-Instruct-v0.2. The resulting models, Suri-SFT and Suri-I-ORPO, generate significantly longer texts (~5K tokens) than base models without significant quality deterioration. Our human evaluation shows that while both SFT and I-ORPO models satisfy most constraints, Suri-I-ORPO generations are generally preferred for their coherent and informative incorporation of the constraints. We release our code at https://github.com/chtmp223/suri.

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 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 12 ran (7 with no instrument failure; 5 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. 1 of the 12 samples that ran has no recorded date.

chtmp223/suri officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 12 ran (5 instrument-failed) · 3 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 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.

2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
5ran
3unverified

Licence: 15 of the 15 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 chtmp223/suri. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

chtmp223/suri official repository 15 samples, 12 ran (5 instrument-failed) · 3 unverified
apply_chat_template in 44 papers ft/lib/alignment_mod/data.py ran no licence file found · pointer only · ed74b164b2fe6a65 · report fixture: signature example:dict/0/?, tokenizer:MockTokenizer/0/?, task:str/0/str, auto_insert_empty_system_msg:bool/0/bool · returned dict · level recorded 2026-09-24
build_generator in 10 papers eval/automatic/ranking.py ran no licence file found · pointer only · 67cf0babead8c2de · report fixture: signature model:callable/0/?, tokenizer:StandInTokenizer/0/?, max_gen_len:int/0/int, use_cache:bool/0/bool · returned function · level recorded 2026-09-24
check_bib utils.py ran · violated contract no licence file found · pointer only · cc64fc0500364fe4 · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-24
convert_to_scalar in 24 papers ft/lib/trl_mod/core.py ran · our draft was wrong no licence file found · pointer only · c32b636f13ed9ee5 · report fixture: signature stats:dict/0/? · returned dict · level recorded 2026-09-25
extract_docstring in 12 papers ft/lib/alignment_mod/decontaminate.py ran · our draft was wrong no licence file found · pointer only · 0edeacd7a9034f53 · report fixture: signature prompt:str/0/str · returned str · level recorded 2026-09-24
is_openai_format in 13 papers ft/lib/alignment_mod/data.py ran · violated contract no licence file found · pointer only · 4253aac010c4504f · report fixture: signature messages:list/1/dict · returned bool · level recorded, date not recorded
load_dataset_column in 10 papers ft/lib/alignment_mod/decontaminate.py ran no licence file found · pointer only · a3791c5c2185e013 · report fixture: returned list · level recorded 2026-09-24
normalize_whitespace in 14 papers ft/lib/alignment_mod/decontaminate.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f43e59d239019e86 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
sequence_prob eval/automatic/ranking.py ran no licence file found · pointer only · 5bffca7d5514764e · report fixture: signature tokenizer:StandInTokenizer/0/?, model:callable/0/?, prompt:str/0/str, response:str/0/str · returned float · level recorded 2026-09-24
strip_trailing_text utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1db337e94d1e9417 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
ft/lib/trl_mod/core.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 5bcf8e086423cf6b · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float, min_tokens_to_keep:int/0/int · returned Tensor · level recorded 2026-09-24
truncating_words utils.py ran fingerprinted no licence file found · pointer only · 9a2951468cd4ee8b · report fixture: signature document:str/0/str, max_tokens:int/0/int · returned str · level recorded 2026-09-24
flatten_dict in 72 papers ft/lib/trl_mod/core.py unverified no licence file found · pointer only · a51ae45a1f6c0b5b · report
is_transformers_greater_than in 9 papers ft/lib/trl_mod/import_utils.py unverified no licence file found · pointer only · 2a9ca02cb6e196ff · report
read_file in 112 papers eval/automatic/ranking.py unverified no licence file found · pointer only · 8f7c20be180ad75b · report

Tasks

FormInstruction FollowingText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASEDPOSFT

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