# Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets

arXiv: https://arxiv.org/abs/2406.08124 · HTML: https://mlsanity.com/paper/2406.08124/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 42 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Reward Model Ensembles Help Mitigate Overoptimization](https://mlsanity.com/paper/2310.02743/) (2023)
- [Visualizing and Measuring the Geometry of BERT](https://mlsanity.com/paper/1906.02715/) (2019)

## Built on by (most cited first, 5 of 5)

- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [On Almost Surely Safe Alignment of Large Language Models at Inference-Time](https://mlsanity.com/paper/2502.01208/) (2025)
- [Can Large Language Models Understand Internet Buzzwords Through User-Generated Content](https://mlsanity.com/paper/2505.15071/) (2025)
- [Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity](https://mlsanity.com/paper/2505.23923/) (2025)
- [Icon2: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation](https://mlsanity.com/paper/2509.05605/) (2025)

## Abstract (arXiv)

The success of the reward model in distinguishing between responses with subtle safety differences depends critically on the high-quality preference dataset, which should capture the fine-grained nuances of harmful and harmless responses. This motivates the need to develop a dataset involving preference margins, which accurately quantify how harmless one response is compared to another. In this paper, we take the first step to propose an effective and cost-efficient framework to promote the margin-enhanced preference dataset development. Our framework, Legend, Leverages representation engineering to annotate preference datasets. It constructs the specific direction within the LLM's embedding space that represents safety. By leveraging this safety direction, Legend can then leverage the semantic distances of paired responses along this direction to annotate margins automatically. We experimentally demonstrate our effectiveness in both reward modeling and harmless alignment for LLMs. Legend also stands out for its efficiency, requiring only the inference time rather than additional training. This efficiency allows for easier implementation and scalability, making Legend particularly valuable for practical applications in aligning LLMs with safe conversations.