SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.00690 · AAAI · 2024

Benchmarking Large Language Models on Controllable Generation under Diversified Instructions

Yi Liu, Quan Wang, Benfeng Xu, Zhendong Mao, Yihan Chen

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 10 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.00690.json · badge: /api/ran/2401.00690.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Xt-cyh/CoDI-Eval canonical (classifier label)
classifier basis: census
13 ran · 5 no recorded run
FunctionStatusWhere it lives
cal_max_avg_toxicity Ran
ran, honoured the contract we drafted
Xt-cyh/CoDI-Eval/statistic.py
pointer only (licence: NONE) · get_code("5049acee0b271f75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

classify_sentiment Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/evaluate.py
pointer only (licence: NONE) · get_code("71e266cfd0e6e573")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

classify_topic Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/evaluate.py
pointer only (licence: NONE) · get_code("174067d7b3c2275d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_text Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/utils/eval_utils.py
pointer only (licence: NONE) · get_code("e551f21cb1015ac1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_data Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/statistic.py
pointer only (licence: NONE) · get_code("280739482fbffd74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_interval Ran
ran, honoured the contract we drafted
Xt-cyh/CoDI-Eval/utils/length_eval.py
pointer only (licence: NONE) · get_code("09c18b0f6797ff78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_test_data Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/evaluate.py
pointer only (licence: NONE) · get_code("cc2b254a5f917403")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_test_data Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/generate.py
pointer only (licence: NONE) · get_code("ac6fcd5d8bf62759")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

number2word Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/utils/length_eval.py
pointer only (licence: NONE) · get_code("39b482520756e734")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_topic_dict Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/utils/query_huggingface.py
pointer only (licence: NONE) · get_code("cd407b6ff1fc7aef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

query Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/utils/query_huggingface.py
pointer only (licence: NONE) · get_code("aa85076767ed9c7a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

query_chatglm Ran
ran; our contract draft was wrong, not the code
Xt-cyh/CoDI-Eval/utils/query_llms.py
pointer only (licence: NONE) · get_code("92ff2d437c56a6f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

query_chatgpt Ran
ran on a synthesized input
Xt-cyh/CoDI-Eval/utils/query_llms.py
pointer only (licence: NONE) · get_code("89f24dd774d0e047")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_meteor Not yet run
unverified (harvested, no recorded run)
Xt-cyh/CoDI-Eval/utils/eval_utils.py
pointer only (licence: NONE) · get_code("4514bd59c017bc70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_open_model Not yet run
unverified (harvested, no recorded run)
Xt-cyh/CoDI-Eval/generate.py
pointer only (licence: NONE) · get_code("850fb04ea11f610e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
Xt-cyh/CoDI-Eval/utils/eval_utils.py
pointer only (licence: NONE) · get_code("ac4e1313c5c2e9c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

query_api_model Not yet run
unverified (harvested, no recorded run)
Xt-cyh/CoDI-Eval/generate.py
pointer only (licence: NONE) · get_code("8aa7d1340bb82140")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

request_query Not yet run
unverified (harvested, no recorded run)
Xt-cyh/CoDI-Eval/utils/query_huggingface.py
pointer only (licence: NONE) · get_code("a54a222cec75c54a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xt-cyh/CoDI-Eval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 18 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a significant aspect of LLM alignment, it is thus important to formulate such a specialized set of instructions as well as investigate the resulting behavior of LLMs. To address this vacancy, we propose a new benchmark CoDI-Eval to systematically and comprehensively evaluate LLMs' responses to instructions with various constraints. We construct a large collection of constraints-attributed instructions as a test suite focused on both generalization and coverage. Specifically, we advocate an instruction diversification process to synthesize diverse forms of constraint expression and also deliberate the candidate task taxonomy with even finer-grained subcategories. Finally, we automate the entire evaluation process to facilitate further developments. Different from existing studies on controllable text generation, CoDI-Eval extends the scope to the prevalent instruction-following paradigm for the first time. We provide extensive evaluations of representative LLMs (e.g., ChatGPT, Vicuna) on CoDI-Eval, revealing their limitations in following instructions with specific constraints and there is still a significant gap between opensource and commercial closed-source LLMs. We believe this benchmark will facilitate research into improving the controllability of LLMs' responses to instructions. Our data and code are available at https://github.com/Xt-cyh/CoDI-Eval.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.00690")
get_code_for_paper("2401.00690")
have("2401.00690")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.00690.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.00690.svg)](https://syntology.ai/paper/2401.00690)

Connect an agent — have() is free.