paper-with-me

Papers

Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation

2026-05-27 · Melih Catal, Alex Wolf, Tiago Ferreiro Matos, Pooja Rani, Harald Gall arxiv

Large Language Models (LLMs) have become an integral part of software development, especially with the advent of agentic capabilities. Yet, many frontier LLMs are affiliated with specific providers. This raises the question of whether generated code favors the provider's own ecosystem over comparable alternatives, potentially constraining developers' choices and increasing dependence on a single provider. We define this behavior as Vertical Integration Bias (VIB) and introduce \textsc{VIBench}, a benchmark for measuring VIB in direct and agentic code generation across $20$ provider-selectable software-integration scenarios. Evaluating $10$ frontier provider-affiliated models against $3$ non-affiliated controls, we find positive VIB in direct generation, with six of ten affiliated models showing statistically significant effects up to $+18.8$ percentage points (pp). Agentic workflows further amplify VIB, reaching $+39.2$ pp. Moreover, early affiliated-ecosystem choices in agentic workflows can persist into conceptually decoupled downstream files, with persistence as high as $90.3\%$. These findings underscore the need to measure and account for VIB in code generation, especially as agentic capabilities become more prevalent.

📄 PDF Abstract BibTeX arXiv:2605.28515

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation

2025-01-14 · XiaoYu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao 외

Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this paper, we reveal a novel provider bias in…

Code GenerationDataset GenerationFairness

Demand for LLMs: Descriptive Evidence on Substitution, Market Expansion, and Multihoming

2025-04-21 · Andrey Fradkin

This paper documents three stylized facts about the demand for Large Language Models (LLMs) using data from OpenRouter, a prominent LLM marketplace. First, new models experience rapid initial adoption that stabilizes wit…

Descriptive

A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression

2019-12-01 · Kai Yang, Tao Fan, Tianjian Chen, Yuanming Shi 외

Data privacy and security becomes a major concern in building machine learning models from different data providers. Federated learning shows promise by leaving data at providers locally and exchanging encrypted informat…

Federated LearningregressionVertical Federated Learning

DS@GT at Touché: Large Language Models for Retrieval-Augmented Debate

2025-07-12 · Anthony Miyaguchi, Conor Johnston, Aaryan Potdar arxiv

Large Language Models (LLMs) demonstrate strong conversational abilities. In this Working Paper, we study them in the context of debating in two ways: their ability to perform in a structured debate along with a dataset …

Vertical Allocation-based Fair Exposure Amortizing in Ranking

2022-04-06 · Tao Yang, Zhichao Xu, Qingyao Ai

Result ranking often affects consumer satisfaction as well as the amount of exposure each item receives in the ranking services. Myopically maximizing customer satisfaction by ranking items only according to relevance wi…

Exposure FairnessFairnessRecommendation Systems