SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.09677 · 2023

R-Tuning: Instructing Large Language Models to Say `I Don't Know'

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 8 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/2311.09677.json · badge: /api/ran/2311.09677.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
shizhediao/r-tuning canonical (classifier label)
classifier basis: census
8 ran · 8 no recorded run
FunctionStatusWhere it lives
calculate_scores Ran
ran, honoured the contract we drafted
shizhediao/r-tuning/evaluation/MMLU/results/calculate_ap.py
pointer only (licence: NONE) · get_code("4215906aecd42093")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_example Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/MMLU/evaluate.py
pointer only (licence: NONE) · get_code("434b759fa0cba061")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_question Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/FEVER/evaluate.py
pointer only (licence: NONE) · get_code("c62af2431eed8398")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_question Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/HaluEvalQA/evaluate.py
pointer only (licence: NONE) · get_code("ed702608cd107f17")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_question Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/HotpotQA/evaluate.py
pointer only (licence: NONE) · get_code("8ffd4f62ece5b520")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_question Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/WiCE/evaluate.py
pointer only (licence: NONE) · get_code("c3a776c309a37593")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_shots Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/MMLU/evaluate.py
pointer only (licence: NONE) · get_code("bb75473fff431fe0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

format_subject Ran
ran; our contract draft was wrong, not the code
shizhediao/r-tuning/evaluation/MMLU/evaluate.py
pointer only (licence: NONE) · get_code("6ab745408cb8648b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

checksure Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/evaluation/FEVER/evaluate.py
pointer only (licence: NONE) · get_code("4b47d29dbb26a5f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/evaluation/FEVER/evaluate.py
pointer only (licence: NONE) · get_code("98a0b6e99d3532df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/evaluation/HaluEvalQA/evaluate.py
pointer only (licence: NONE) · get_code("463dd7fbdb3230ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/evaluation/HotpotQA/evaluate.py
pointer only (licence: NONE) · get_code("73ec093e1e84c7d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/evaluation/WiCE/evaluate.py
pointer only (licence: NONE) · get_code("b67471c3a3591add")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/evaluation/pararel/evaluate.py
pointer only (licence: NONE) · get_code("57cbd3b83c4e5ef1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/training/FEVER/run_fever.py
pointer only (licence: NONE) · get_code("9895a60c8ddb2794")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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.

inference Not yet run
unverified (harvested, no recorded run)
shizhediao/r-tuning/training/HotpotQA/run_hotpotqa.py
pointer only (licence: NONE) · get_code("34083253ed1953e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shizhediao/r-tuning 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 14 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.

FunctionAlso present inEarliest-datedOthers named
format_subject 21 other papers
5 dated earlier, 16 later
2009.03300 (2020-09)
Measuring Massive Multitask Language Understanding
2304.12986 (2023-04)
Measuring Massive Multitask Chinese Understanding
2305.17306 (2023-05)
Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
and 18 more not named here

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

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed hallucination. Our research is motivated by the observation that previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. When the question is out of the parametric knowledge, it will try to make up something and fail to indicate when it lacks knowledge. In this paper, we present a new approach called Refusal-Aware Instruction Tuning (R-Tuning). This approach is formalized by first identifying the disparity in knowledge encompassed by pre-trained parameters compared to that of instruction tuning data. Then, we construct the refusal-aware data based on the knowledge intersection, to tune LLMs to refrain from responding to questions beyond its parametric knowledge. Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions. Furthermore, when tested on out-of-domain datasets, the refusal ability was found to be a meta-skill that could be generalized to other tasks. Further analysis surprisingly finds that learning the uncertainty results in better calibration and an improved ability to estimate the uncertainty than uncertainty-based testing. Our code is available at https://github.com/shizhediao/R-Tuning.

For agents

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

get_harvested_code_for_paper("2311.09677")
get_code_for_paper("2311.09677")
have("2311.09677")

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

curl https://syntology.ai/api/ran/2311.09677.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.09677.svg)](https://syntology.ai/paper/2311.09677)

Connect an agent — have() is free.