# Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation

arXiv: https://arxiv.org/abs/2506.10403 · HTML: https://mlsanity.com/paper/2506.10403/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [QuRating: Selecting High-Quality Data for Training Language Models](https://mlsanity.com/paper/2402.09739/) (2024)
- [Training Complex Models with Multi-Task Weak Supervision](https://mlsanity.com/paper/1810.02840/) (2018)
- [Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods](https://mlsanity.com/paper/2002.11955/) (2020)
- [Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates](https://mlsanity.com/paper/2408.13006/) (2024)
- [FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge](https://mlsanity.com/paper/2305.08281/) (2023)
- [Weak-to-Strong Generalization Through the Data-Centric Lens](https://mlsanity.com/paper/2412.03881/) (2024)
- [Discovering Bias in Latent Space: An Unsupervised Debiasing Approach](https://mlsanity.com/paper/2406.03631/) (2024)
- [Lifting Weak Supervision To Structured Prediction](https://mlsanity.com/paper/2211.13375/) (2022)
- [The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators](https://mlsanity.com/paper/2407.11004/) (2024)
- [AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels](https://mlsanity.com/paper/2208.14362/) (2022)
- [ScriptoriumWS: A Code Generation Assistant for Weak Supervision](https://mlsanity.com/paper/2502.12366/) (2025)

## Built on by (most cited first, 6 of 6)

- [CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation](https://mlsanity.com/paper/2603.00039/) (2026)
- [Automating Benchmark Design](https://mlsanity.com/paper/2510.25039/) (2025)
- [Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation](https://mlsanity.com/paper/2604.05083/) (2026)
- [Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation](https://mlsanity.com/paper/2604.04532/) (2026)
- [TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning](https://mlsanity.com/paper/2607.26977/) (2026)
- [JudgeMoE: Distributional Aggregation for LLM-as-a-Judge](https://mlsanity.com/paper/2610.07109/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are widely used to evaluate the quality of LLM generations and responses, but this leads to significant challenges: high API costs, uncertain reliability, inflexible pipelines, and inherent biases. To address these, we introduce PAJAMA (Program-As-a-Judge for Automated Model Assessment), a new alternative that uses LLMs to synthesize executable judging programs instead of directly scoring responses. These synthesized programs can be stored and run locally, costing orders of magnitude less while providing interpretable, and auditable judging logic that can be easily adapted. Program-based judges mitigate biases, improving judgment consistency by 15.83% and reducing biased responses by 23.7% on average compared to a Qwen2.5-14B-based LLM-as-a-judge. When program judgments are distilled into a model, PAJAMA outperforms LLM-as-a-judge on the challenging CHAT-HARD subset of RewardBench, outperforming metrics by 2.19% on Prometheus and 8.67% on the JudgeLM dataset, all at three orders of magnitude lower cost.