# Atla Selene Mini: A General Purpose Evaluation Model

arXiv: https://arxiv.org/abs/2501.17195 · HTML: https://mlsanity.com/paper/2501.17195/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2025.

## Built on by (most cited first, 27 of 27)

- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning](https://mlsanity.com/paper/2505.10320/) (2025)
- [Reward Reasoning Model](https://mlsanity.com/paper/2505.14674/) (2025)
- [Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings](https://mlsanity.com/paper/2503.15620/) (2025)
- [The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors](https://mlsanity.com/paper/2509.04484/) (2025)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [Sherlock: Reliable and Efficient Agentic Workflow Execution](https://mlsanity.com/paper/2511.00330/) (2025)
- [Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization](https://mlsanity.com/paper/2603.08091/) (2026)
- [InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context](https://mlsanity.com/paper/2502.12257/) (2025)
- [Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey](https://mlsanity.com/paper/2510.01925/) (2025)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2508.05613/) (2025)
- [DISCO: Disentangled Communication Steering for Large Language Models](https://mlsanity.com/paper/2509.16820/) (2025)
- [Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains](https://mlsanity.com/paper/2510.17793/) (2025)
- [Reference-Free Rating of LLM Responses via Latent Information](https://mlsanity.com/paper/2509.24678/) (2025)
- [XBreaking: Understanding how LLMs security alignment can be broken](https://mlsanity.com/paper/2504.21700/) (2025)
- [A Finite-Calibration Regime Map for LLM Judge Panels](https://mlsanity.com/paper/2606.01034/) (2026)
- [Stopping and Routing LLM Judge Panels](https://mlsanity.com/paper/2608.19802/) (2026)
- [Small Language Models as Judges for Rubric-Based Reinforcement Learning](https://mlsanity.com/paper/2608.30005/) (2026)
- [SecureBreak -- A dataset towards safe and secure models](https://mlsanity.com/paper/2603.21975/) (2026)
- [Comparing Developer and LLM Biases in Code Evaluation](https://mlsanity.com/paper/2603.24586/) (2026)
- [Model selection meets clinical semantics: Optimizing ICD-10-CM prediction via LLM-as-Judge evaluation, redundancy-aware sampling, and section-aware fine-tuning](https://mlsanity.com/paper/2509.18846/) (2025)
- [Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering](https://mlsanity.com/paper/2510.18691/) (2025)
- [VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference](https://mlsanity.com/paper/2605.11334/) (2026)
- [Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregation](https://mlsanity.com/paper/2606.03128/) (2026)
- [Counsel: A Meta-Evaluation Dataset for Agentic Tasks](https://mlsanity.com/paper/2606.21627/) (2026)
- [Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds](https://mlsanity.com/paper/2607.28908/) (2026)

## Abstract (arXiv)

We introduce Atla Selene Mini, a state-of-the-art small language model-as-a-judge (SLMJ). Selene Mini is a general-purpose evaluator that outperforms the best SLMJs and GPT-4o-mini on overall performance across 11 out-of-distribution benchmarks, spanning absolute scoring, classification, and pairwise preference tasks. It is the highest-scoring 8B generative model on RewardBench, surpassing strong baselines like GPT-4o and specialized judges. To achieve this, we develop a principled data curation strategy that augments public datasets with synthetically generated critiques and ensures high quality through filtering and dataset ablations. We train our model on a combined direct preference optimization (DPO) and supervised fine-tuning (SFT) loss, and produce a highly promptable evaluator that excels in real-world scenarios. Selene Mini shows dramatically improved zero-shot agreement with human expert evaluations on financial and medical industry datasets. It is also robust to variations in prompt format. Preliminary results indicate that Selene Mini is the top-ranking evaluator in a live, community-driven Judge Arena. We release the model weights on HuggingFace (https://hf.co/AtlaAI/Selene-1-Mini-Llama-3.1-8B) and Ollama to encourage widespread community adoption.