# Alignment midtraining for animals

arXiv: https://arxiv.org/abs/2604.13076 · HTML: https://mlsanity.com/paper/2604.13076/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 30 of 32)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity](https://mlsanity.com/paper/2305.13169/) (2023)
- [Linear Representations of Sentiment in Large Language Models](https://mlsanity.com/paper/2310.15154/) (2023)
- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [Subliminal Learning: Language models transmit behavioral traits via hidden signals in data](https://mlsanity.com/paper/2507.14805/) (2025)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Persona Features Control Emergent Misalignment](https://mlsanity.com/paper/2506.19823/) (2025)
- [Auditing language models for hidden objectives](https://mlsanity.com/paper/2503.10965/) (2025)
- [Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples](https://mlsanity.com/paper/2510.07192/) (2025)
- [Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs](https://mlsanity.com/paper/2512.09742/) (2025)
- [Language Models Resist Alignment: Evidence From Data Compression](https://mlsanity.com/paper/2406.06144/) (2024)
- [Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment](https://mlsanity.com/paper/2510.05024/) (2025)
- [On the generalization of language models from in-context learning and finetuning: a controlled study](https://mlsanity.com/paper/2505.00661/) (2025)
- [Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment](https://mlsanity.com/paper/2601.10160/) (2026)
- [Dissecting Fine-Tuning Unlearning in Large Language Models](https://mlsanity.com/paper/2410.06606/) (2024)
- [Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls](https://mlsanity.com/paper/2510.01631/) (2025)
- [Believe It or Not: How Deeply do LLMs Believe Implanted Facts?](https://mlsanity.com/paper/2510.17941/) (2025)
- [On Linear Representations and Pretraining Data Frequency in Language Models](https://mlsanity.com/paper/2504.12459/) (2025)
- [How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization](https://mlsanity.com/paper/2501.13669/) (2025)
- [The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models](https://mlsanity.com/paper/2509.10970/) (2025)
- [Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility](https://mlsanity.com/paper/2507.11630/) (2025)
- [How far can bias go? Tracing bias from pretraining data to alignment](https://mlsanity.com/paper/2411.19240/) (2024)
- [The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs](https://mlsanity.com/paper/2511.20104/) (2025)

## Built on by (most cited first, 4 of 4)

- [Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation](https://mlsanity.com/paper/2607.15434/) (2026)
- [Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning](https://mlsanity.com/paper/2605.16301/) (2026)
- [Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training](https://mlsanity.com/paper/2606.26102/) (2026)
- [HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals](https://mlsanity.com/paper/2609.04444/) (2026)

## Abstract (arXiv)

We investigate the robustness of value alignment via midtraining with synthetic documents, using animal compassion as a value that is both important in its own right and orthogonal to existing alignment efforts. To evaluate compassionate reasoning, we develop and publicly release Animal Norms In Moral Assessment (ANIMA), a 26-question evaluation spanning 13 ethical dimensions, publicly available as a dataset and Inspect evaluation. On ANIMA, training with 3000 documents achieves 77% compared to 40% for instruction-tuning approaches, with generalization to human compassion and no degradation in standard safety benchmarks or capabilities. However, subsequent unrelated instruction-tuning degrades the intervention, with the advantage disappearing after 5000 samples. Our exploratory results suggest document-based value interventions may require explicit preservation strategies to remain effective through typical training pipelines.