# Structuring the Space of Sociotechnical Alignment

arXiv: https://arxiv.org/abs/2607.01250 · HTML: https://mlsanity.com/paper/2607.01250/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 181 of its 305 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 30 of 181)

- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [Removing RLHF Protections in GPT-4 via Fine-Tuning](https://mlsanity.com/paper/2311.05553/) (2023)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards](https://mlsanity.com/paper/2402.18571/) (2024)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [Direct Preference Optimization with an Offset](https://mlsanity.com/paper/2402.10571/) (2024)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [SeaLLMs -- Large Language Models for Southeast Asia](https://mlsanity.com/paper/2312.00738/) (2023)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing](https://mlsanity.com/paper/2405.18166/) (2024)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion](https://mlsanity.com/paper/2403.07865/) (2024)
- [AceGPT, Localizing Large Language Models in Arabic](https://mlsanity.com/paper/2309.12053/) (2023)
- [Intention Analysis Makes LLMs A Good Jailbreak Defender](https://mlsanity.com/paper/2401.06561/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters](https://mlsanity.com/paper/2410.24190/) (2024)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [Unintended Impacts of LLM Alignment on Global Representation](https://mlsanity.com/paper/2402.15018/) (2024)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [Benchmarking Distributional Alignment of Large Language Models](https://mlsanity.com/paper/2411.05403/) (2024)
- [One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity](https://mlsanity.com/paper/2411.04427/) (2024)
- [Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation](https://mlsanity.com/paper/2305.00955/) (2023)

## Built on by (most cited first, 2 of 2)

- [Structuring the Space of Perspectives](https://mlsanity.com/paper/2608.12113/) (2026)
- [Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment](https://mlsanity.com/paper/2609.26929/) (2026)

## Abstract (arXiv)

Sociotechnical alignment concerns the social desirability of AI behavior and is thus inherently normative, not merely technical. While NLP research increasingly addresses its technical aspects, it often leaves underspecified what such "social desirability" entails. We argue that this reflects a fundamental gap: the absence of a systematic way to specify how sociotechnical alignment defines, justifies, and evaluates socially desirable AI behavior. To address this gap, we introduce a human-centered framework for specifying sociotechnical alignment. We draw on social-scientific accounts of sociobehavioral desirability to ground the basis for behavioral desirability judgments and use this framework to analyze how alignment is specified in practice. Our systematic literature review identifies recurring patterns: normative concepts grounding desirability judgments are often unspecified or conflated with alignment targets for (desired) system behavior, target populations are underdefined, and design choices are rarely theoretically justified. These findings point to a lack of conceptual specificity that limits cumulative progress. We therefore offer recommendations that link social-scientific frameworks to alignment design choices, supporting more conceptually precise approaches to sociotechnical alignment.