# Comparing Developer and LLM Biases in Code Evaluation

arXiv: https://arxiv.org/abs/2603.24586 · HTML: https://mlsanity.com/paper/2603.24586/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 74 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 30 of 51)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs](https://mlsanity.com/paper/2406.10216/) (2024)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development](https://mlsanity.com/paper/2302.07080/) (2023)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges](https://mlsanity.com/paper/2303.17125/) (2023)
- [Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering](https://mlsanity.com/paper/2502.06193/) (2025)
- [A Survey on Evaluating Large Language Models in Code Generation Tasks](https://mlsanity.com/paper/2408.16498/) (2024)
- [Inverse Constitutional AI: Compressing Preferences into Principles](https://mlsanity.com/paper/2406.06560/) (2024)
- [EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations](https://mlsanity.com/paper/2410.22821/) (2024)
- [Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support](https://mlsanity.com/paper/2502.18658/) (2025)
- [Direct Judgement Preference Optimization](https://mlsanity.com/paper/2409.14664/) (2024)
- [CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks](https://mlsanity.com/paper/2507.10535/) (2025)
- [Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows](https://mlsanity.com/paper/2507.08149/) (2025)
- [Atla Selene Mini: A General Purpose Evaluation Model](https://mlsanity.com/paper/2501.17195/) (2025)
- [EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code](https://mlsanity.com/paper/2505.13004/) (2025)
- [Copilot Arena: A Platform for Code LLM Evaluation in the Wild](https://mlsanity.com/paper/2502.09328/) (2025)

## Built on by (most cited first, 1 of 1)

- [CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging](https://mlsanity.com/paper/2605.19665/) (2026)

## Abstract (arXiv)

As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and models weigh each item. Across three modalities -- chat-based programming, IDE autocompletion, and instructed code editing -- we use TRACE to measure how well LLM judges align with developer preferences. Among 13 different models, the best judges underperform human annotators by 12-23%. TRACE identifies 35 significant sources of misalignment between humans and judges across interaction modalities, the majority of which correspond to existing software engineering code quality criteria. For example, in chat-based coding, judges are biased towards longer code explanations while humans prefer shorter ones. We find significant misalignment on the majority of existing code quality dimensions, showing alignment gaps between LLM judges and human preference in realistic coding applications.