SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.03314 · 2026

Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO

Xin Yang, Xuxin Cheng, Xunliang Cai, Abudukelimu Wuerkaixi, Ke Zeng, Cao Liu, Letian Li, Wenyuan Jiang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; 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/2603.03314.json · badge: /api/ran/2603.03314.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
vegetable-yx/CoIPO community
Papers with Code archive
2 ran · 3 no recorded run
FunctionStatusWhere it lives
ContrastiveLoss Ran
ran on a synthesized input
vegetable-yx/CoIPO/ContrastiveLlama.py
pointer only (licence: NONE) · get_code("d9cf256672b2d843")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vegetable-yx/CoIPO 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.

separate_batch_prompts Ran
ran; our contract draft was wrong, not the code
vegetable-yx/CoIPO/ContrastiveLlama.py
pointer only (licence: NONE) · get_code("56739640fa432aa6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vegetable-yx/CoIPO 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.

ContrastiveEvalOutput Not yet run
unverified (harvested, no recorded run)
vegetable-yx/CoIPO/ContrastiveLlama.py
pointer only (licence: NONE) · get_code("e449146d4745cc0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vegetable-yx/CoIPO 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.

ContrastiveLlama Not yet run
unverified (harvested, no recorded run)
vegetable-yx/CoIPO/ContrastiveLlama.py
pointer only (licence: NONE) · get_code("043084a51b2808ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vegetable-yx/CoIPO 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.

ContrastiveLlamaOutput Not yet run
unverified (harvested, no recorded run)
vegetable-yx/CoIPO/ContrastiveLlama.py
pointer only (licence: NONE) · get_code("a7306c4b87c799f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vegetable-yx/CoIPO 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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, 0 later) and 4 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
separate_batch_prompts
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2402.11138 (2024-02)
Contrastive Instruction Tuning

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 demonstrated remarkable and steadily improving performance across a wide range of tasks. However, LLM performance may be highly sensitive to prompt variations especially in scenarios with limited openness or strict output formatting requirements, indicating insufficient robustness. In real-world applications, user prompts provided to LLMs often contain imperfections, which may undermine the quality of the model's responses. To address this issue, previous work has primarily focused on preprocessing prompts, employing external tools or even LLMs to refine prompt formulations in advance. However, these approaches overlook the intrinsic robustness of LLMs, and their reliance on external components introduces additional computational overhead and uncertainty. In this work, we propose a Contrastive Learning-based Inverse Direct Preference Optimization (CoIPO) method that minimizes the discrepancy between the label-aligned logits produced by the model under a clean prompt and its noisy counterpart, and conduct a detailed analysis using mutual information theory. We augment the FLAN dataset by constructing paired prompts, each consisting of a clean prompt and its corresponding noisy version for training. Additionally, to evaluate the effectiveness, we develop NoisyPromptBench, a benchmark enhanced and derived from the existing PromptBench. Experimental results conducted on NoisyPromptBench demonstrate that our proposed method achieves a significant improvement in average accuracy over the current state-of-the-art approaches. The source code of CoIPO, pair-wise FLAN datasets, and NoisyPromptBench have already been released on https://github.com/vegetable-yx/CoIPO.

For agents

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

get_harvested_code_for_paper("2603.03314")
get_code_for_paper("2603.03314")
have("2603.03314")

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

curl https://syntology.ai/api/ran/2603.03314.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.03314.svg)](https://syntology.ai/paper/2603.03314)

Connect an agent — have() is free.