# LLM Reinforcement in Context

arXiv: https://arxiv.org/abs/2511.12782 · HTML: https://mlsanity.com/paper/2511.12782/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)

## Builds on (most cited first, 22 of 22)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Large Language Models in Finance: A Survey](https://mlsanity.com/paper/2311.10723/) (2023)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)
- [Reinforcement Learning for LLM Post-Training: A Survey](https://mlsanity.com/paper/2407.16216/) (2024)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [On the Diversity of Synthetic Data and its Impact on Training Large Language Models](https://mlsanity.com/paper/2410.15226/) (2024)
- [Bayesian Reward Models for LLM Alignment](https://mlsanity.com/paper/2402.13210/) (2024)
- [SPRIG: Improving Large Language Model Performance by System Prompt Optimization](https://mlsanity.com/paper/2410.14826/) (2024)
- [Mission Impossible: A Statistical Perspective on Jailbreaking LLMs](https://mlsanity.com/paper/2408.01420/) (2024)
- [Long Context Alignment with Short Instructions and Synthesized Positions](https://mlsanity.com/paper/2405.03939/) (2024)
- [PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs](https://mlsanity.com/paper/2409.14866/) (2024)
- [Adversarial Preference Learning for Robust LLM Alignment](https://mlsanity.com/paper/2505.24369/) (2025)
- [Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem](https://mlsanity.com/paper/2506.17299/) (2025)
- [Exploiting Input Sanitization for Regex Denial of Service](https://mlsanity.com/paper/2303.01996/) (2023)

## Abstract (arXiv)

Current Large Language Model alignment research mostly focuses on improving model robustness against adversarial attacks and misbehavior by training on examples and prompting. Research has shown that LLM jailbreak probability increases with the size of the user input or conversation length. There is a lack of appropriate research into means of strengthening alignment which also scale with user input length. We propose interruptions as a possible solution to this problem. Interruptions are control sentences added to the user input approximately every x tokens for some arbitrary x. We suggest that this can be generalized to the Chain-of-Thought process to prevent scheming.