# Prompt-Based Value Steering of Large Language Models

arXiv: https://arxiv.org/abs/2511.16688 · HTML: https://mlsanity.com/paper/2511.16688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Prompt Engineering a Prompt Engineer](https://mlsanity.com/paper/2311.05661/) (2023)
- [MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks](https://mlsanity.com/paper/2310.19677/) (2023)
- [A Survey of Automatic Prompt Engineering: An Optimization Perspective](https://mlsanity.com/paper/2502.11560/) (2025)
- [ValueNet: A New Dataset for Human Value Driven Dialogue System](https://mlsanity.com/paper/2112.06346/) (2021)
- [Commonsense-Focused Dialogues for Response Generation: An Empirical Study](https://mlsanity.com/paper/2109.06427/) (2021)
- [The Touch'e23-ValueEval Dataset for Identifying Human Values behind Arguments](https://mlsanity.com/paper/2301.13771/) (2023)
- [Normative Evaluation of Large Language Models with Everyday Moral Dilemmas](https://mlsanity.com/paper/2501.18081/) (2025)
- [GAAPO: Genetic Algorithmic Applied to Prompt Optimization](https://mlsanity.com/paper/2504.07157/) (2025)
- [Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values](https://mlsanity.com/paper/2501.07071/) (2025)
- [Vision Language Models as Values Detectors](https://mlsanity.com/paper/2501.03957/) (2025)

## Abstract (arXiv)

Large language models are increasingly used in applications where alignment with human values is critical. While model fine-tuning is often employed to ensure safe responses, this technique is static and does not lend itself to everyday situations involving dynamic values and preferences. In this paper, we present a practical, reproducible, and model-agnostic procedure to evaluate whether a prompt candidate can effectively steer generated text toward specific human values, formalising a scoring method to quantify the presence and gain of target values in generated responses. We apply our method to a variant of the Wizard-Vicuna language model, using Schwartz's theory of basic human values and a structured evaluation through a dialogue dataset. With this setup, we compare a baseline prompt to one explicitly conditioned on values, and show that value steering is possible even without altering the model or dynamically optimising prompts.