# No Generation without Representation: Efficient Causal Protein Language Models Enable Zero-Shot Fitness Estimation

arXiv: https://arxiv.org/abs/2602.01845 · HTML: https://mlsanity.com/paper/2602.01845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 82 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Evaluating Protein Transfer Learning with TAPE](https://mlsanity.com/paper/1906.08230/) (2019)
- [Primer: Searching for Efficient Transformers for Language Modeling](https://mlsanity.com/paper/2109.08668/) (2021)
- [Round and Round We Go! What makes Rotary Positional Encodings useful?](https://mlsanity.com/paper/2410.06205/) (2024)
- [A Spectral Condition for Feature Learning](https://mlsanity.com/paper/2310.17813/) (2023)
- [NorMuon: Making Muon more efficient and scalable](https://mlsanity.com/paper/2510.05491/) (2025)
- [Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective](https://mlsanity.com/paper/2410.05192/) (2024)
- [InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2412.12101/) (2024)
- [Rope to Nope and Back Again: A New Hybrid Attention Strategy](https://mlsanity.com/paper/2501.18795/) (2025)
- [Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers](https://mlsanity.com/paper/2512.17351/) (2025)
- [PoET: A generative model of protein families as sequences-of-sequences](https://mlsanity.com/paper/2306.06156/) (2023)
- [Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings](https://mlsanity.com/paper/2509.10534/) (2025)
- [Understanding protein function with a multimodal retrieval-augmented foundation model](https://mlsanity.com/paper/2508.04724/) (2025)
- [ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders](https://mlsanity.com/paper/2509.05309/) (2025)

## Abstract (arXiv)

Protein language models (PLMs) face a fundamental divide: masked language models (MLMs) excel at fitness prediction while causal models enable generation, forcing practitioners to maintain separate architectures. We introduce Proust, a 309M-parameter causal PLM that bridges this gap through architectural innovations adapted from recent LLM research, including grouped-query attention with shared K/V projections, cross-layer value residuals, and depthwise causal convolutions. Trained on 33B tokens in 40 B200 GPU-hours, Proust achieves Spearman ρ = 0.390 on ProteinGym substitutions, competitive with MLMs requiring 50--200× the compute. On indels, Proust sets a new state-of-the-art, outperforming models up to 20× larger. On EVEREST viral fitness benchmarks, it approaches structure-aware methods using sequence alone. These powerful representations position Proust in a sweet spot as it also retains native generative capabilities that MLMs lack by design. Interpretability analysis reveals that per-position entropy variance predicts, to an extent, when retrieval augmentation helps and hurts. Such insights can grow in both quantity and quality at scale and inform capabilities such as test-time scaling. Code and weights are available at https://github.com/Furkan9015/proust-inference