SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11436 · ACL · 2024

Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement

Lei Li, William Wang, Wenda Xu, Xuandong Zhao, Liangming Pan, Guanglei Zhu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2402.11436.json · badge: /api/ran/2402.11436.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
xu1998hz/llm_self_bias canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_nll Ran
ran, honoured the contract we drafted
xu1998hz/llm_self_bias/code/load_models.py
pointer only (licence: NONE) · get_code("7d15fc9eedf8949b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xu1998hz/llm_self_bias 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.

distance_skewness Ran
ran, honoured the contract we drafted
xu1998hz/llm_self_bias/code/compute_bias.py
pointer only (licence: NONE) · get_code("facb754dd4ad9ccd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xu1998hz/llm_self_bias 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_string Ran
ran; our contract draft was wrong, not the code
xu1998hz/llm_self_bias/code/compute_bias_reasoning.py
pointer only (licence: NONE) · get_code("c3aa85b5184ceb55")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xu1998hz/llm_self_bias 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.

skewness Ran
ran, violated the contract we drafted
xu1998hz/llm_self_bias/code/compute_bias.py
pointer only (licence: NONE) · get_code("1a2c83e0cfdc944c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xu1998hz/llm_self_bias 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary is due to LLM's bias in evaluating their own output. In this paper, we formally define LLM's self-bias -the tendency to favor its own generation -using two statistics. We analyze six LLMs (GPT-4, GPT-3.5, Gemini, LLaMA2, Mixtral and DeepSeek) on translation, constrained text generation, and mathematical reasoning tasks. We find that self-bias is prevalent in all examined LLMs across multiple languages and tasks. Our analysis reveals that while the self-refine pipeline improves the fluency and understandability of model outputs, it further amplifies self-bias. To mitigate such biases, we discover that larger model size and external feedback with accurate assessment can significantly reduce bias in the self-refine pipeline, leading to actual performance improvement in downstream tasks. The code and data are released at https://github. com/xu1998hz/llm_self_bias.

For agents

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

get_harvested_code_for_paper("2402.11436")
get_code_for_paper("2402.11436")
have("2402.11436")

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

curl https://syntology.ai/api/ran/2402.11436.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11436.svg)](https://syntology.ai/paper/2402.11436)

Connect an agent — have() is free.