On the public citation graph

Research Agenda for Sociotechnical Approaches to AI Safety

https://doi.org/10.2139/ssrn.5097286
0 signed · 138 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.
Claim with ORCID
Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.
See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/978-3-030-18050-8_14openalex-snapshot
Agent-Mediated Social Choice
inferredcites →https://doi.org/10.1007/978-3-031-43264-4_11openalex-snapshot
SHAPE: A Framework for Evaluating the Ethicality of Influence
inferredcites →https://doi.org/10.1007/s00146-017-0760-1openalex-snapshot
Social choice ethics in artificial intelligence
inferredcites →https://doi.org/10.1007/s10676-017-9430-8openalex-snapshot
Society-in-the-loop: programming the algorithmic social contract
inferredcites →https://doi.org/10.1007/s40593-022-00293-3openalex-snapshot
Integrating Ethics and Career Futures with Technical Learning to Promote AI Literacy for Middle School Students: An Exploratory Study
inferredcites →https://doi.org/10.1016/j.patter.2021.100336openalex-snapshot
Data and its (dis)contents: A survey of dataset development and use in machine learning research
inferredcites →https://doi.org/10.1016/j.patter.2024.100988openalex-snapshot
AI deception: A survey of examples, risks, and potential solutions
inferredcites →https://doi.org/10.1016/j.techfore.2016.08.019openalex-snapshot
The future of employment: How susceptible are jobs to computerisation?
inferredcites →https://doi.org/10.1016/s2589-7500(21)00208-9openalex-snapshot
The false hope of current approaches to explainable artificial intelligence in health care
inferredcites →https://doi.org/10.1017/can.2021.23openalex-snapshot
What’s Wrong with Automated Influence
inferredcites →https://doi.org/10.1017/cbo9781107446984openalex-snapshot
Handbook of Computational Social Choice
inferredcites →https://doi.org/10.1017/xps.2020.37openalex-snapshot
All the News That’s Fit to Fabricate: AI-Generated Text as a Tool of Media Misinformation
inferredcites →https://doi.org/10.1038/s41598-023-30938-9openalex-snapshot
Artificial intelligence in communication impacts language and social relationships
inferredcites →https://doi.org/10.1038/s42256-023-00692-8openalex-snapshot
Explaining machine learning models with interactive natural language conversations using TalkToModel
inferredcites →https://doi.org/10.1073/pnas.2212270120openalex-snapshot
On the rise of fear speech in online social media
inferredcites →https://doi.org/10.1073/pnas.2318124121openalex-snapshot
Evaluating language models for mathematics through interactions
inferredcites →https://doi.org/10.1080/1369118x.2012.678878openalex-snapshot
CRITICAL QUESTIONS FOR BIG DATA
inferredcites →https://doi.org/10.1080/17579961.2021.1898310openalex-snapshot
The dark side of the ‘Moral Machine’ and the fallacy of computational ethical decision-making for autonomous vehicles
inferredcites →https://doi.org/10.1086/705716openalex-snapshot
Robots and Jobs: Evidence from US Labor Markets
inferredcites →https://doi.org/10.1093/oso/9780198909460.003.0002openalex-snapshot
Legitimacy, Authority, and Democratic Duties of Explanation
inferredcites →https://doi.org/10.1109/2.910905openalex-snapshot
How computer systems embody values
inferredcites →https://doi.org/10.1109/sp46215.2023.10179300openalex-snapshot
Analyzing Leakage of Personally Identifiable Information in Language Models
inferredcites →https://doi.org/10.1111/1467-9655.13479openalex-snapshot
Everything lies in a space: cultural data and spatial reality
inferredcites →https://doi.org/10.1111/nous.12424openalex-snapshot
Is there an epistemic advantage to being oppressed?
inferredcites →https://doi.org/10.1111/phc3.12964openalex-snapshot
Artificial Intelligence: Arguments for Catastrophic Risk
inferredcites →https://doi.org/10.1126/science.abi7176openalex-snapshot
Filling gaps in trustworthy development of AI
inferredcites →https://doi.org/10.1126/science.adi8982openalex-snapshot
AI safety on whose terms?
inferredcites →https://doi.org/10.1126/science.adn0117openalex-snapshot
Managing extreme AI risks amid rapid progress
inferredcites →https://doi.org/10.1145/2090236.2090255openalex-snapshot
Fairness through awareness
inferredcites →https://doi.org/10.1145/2470654.2470742openalex-snapshot
Turkopticon
inferredcites →https://doi.org/10.1145/3274357openalex-snapshot
The Misgendering Machines
inferredcites →https://doi.org/10.1145/3287560.3287598openalex-snapshot
Fairness and Abstraction in Sociotechnical Systems
inferredcites →https://doi.org/10.1145/3306618.3314232openalex-snapshot
"Scary Robots"
inferredcites →https://doi.org/10.1145/3306618.3314244openalex-snapshot
Actionable Auditing
inferredcites →https://doi.org/10.1145/3306618.3314250openalex-snapshot
Incomplete Contracting and AI Alignment
inferredcites →https://doi.org/10.1145/3313831.3376293openalex-snapshot
Digital Juries: A Civics-Oriented Approach to Platform Governance
inferredcites →https://doi.org/10.1145/3375627.3375803openalex-snapshot
Beyond Near- and Long-Term
inferredcites →https://doi.org/10.1145/3375627.3375820openalex-snapshot
Saving Face
inferredcites →https://doi.org/10.1145/3375627.3375861openalex-snapshot
Hard Choices in Artificial Intelligence
inferredcites →https://doi.org/10.1145/3411764.3445717openalex-snapshot
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
inferredcites →https://doi.org/10.1145/3433949openalex-snapshot
The (Im)possibility of fairness
inferredcites →https://doi.org/10.1145/3491102.3502004openalex-snapshot
Jury Learning: Integrating Dissenting Voices into Machine Learning Models
inferredcites →https://doi.org/10.1145/3512929openalex-snapshot
Comparing the Perceived Legitimacy of Content Moderation Processes: Contractors, Algorithms, Expert Panels, and Digital Juries
inferredcites →https://doi.org/10.1145/3531146.3533083openalex-snapshot
The Values Encoded in Machine Learning Research
inferredcites →https://doi.org/10.1145/3531146.3533137openalex-snapshot
Making the Unaccountable Internet: The Changing Meaning of Accounting in the Early ARPANET
inferredcites →https://doi.org/10.1145/3551624.3555290openalex-snapshot
Power to the People? Opportunities and Challenges for Participatory AI
inferredcites →https://doi.org/10.1145/3579612openalex-snapshot
Improving Human-AI Collaboration With Descriptions of AI Behavior
inferredcites →https://doi.org/10.1145/3593013.3594033openalex-snapshot
Harms from Increasingly Agentic Algorithmic Systems
inferredcites →https://doi.org/10.1145/3600211.3604669openalex-snapshot
User Tampering in Reinforcement Learning Recommender Systems
inferredcites →https://doi.org/10.1145/3600211.3604692openalex-snapshot
Human Uncertainty in Concept-Based AI Systems
inferredcites →https://doi.org/10.1145/3617694.3623226openalex-snapshot
Characterizing Manipulation from AI Systems
inferredcites →https://doi.org/10.1145/3630106.3658979openalex-snapshot
Collective Constitutional AI: Aligning a Language Model with Public Input
inferredcites →https://doi.org/10.1145/3670865.3673547openalex-snapshot
Generative Social Choice
inferredcites →https://doi.org/10.1146/annurev-statistics-042720-125902openalex-snapshot
Algorithmic Fairness: Choices, Assumptions, and Definitions
inferredcites →https://doi.org/10.1177/01622439211030007openalex-snapshot
Talking AI into Being: The Narratives and Imaginaries of National AI Strategies and Their Performative Politics
inferredcites →https://doi.org/10.1177/1470594x14544284openalex-snapshot
Deliberation and disagreement
inferredcites →https://doi.org/10.1201/9781003278290-21openalex-snapshot
Wrongfully Accused by an Algorithm *
inferredcites →https://doi.org/10.13140/rg.2.2.13256.70408openalex-snapshot
THE TRICKLE-DOWN IMPACT OF REWARD (IN-)CONSISTENCY ON RLHF
inferredcites →https://doi.org/10.1353/jod.2023.a907697openalex-snapshot
Reimagining Democracy for AI
inferredcites →https://doi.org/10.14763/2022.1.1652openalex-snapshot
Systematic review: YouTube recommendations and problematic content
inferredcites →https://doi.org/10.15779/z38bg31openalex-snapshot
Big Data's Disparate Impact
inferredcites →https://doi.org/10.1609/aaai.v32i1.11512openalex-snapshot
A Voting-Based System for Ethical Decision Making
inferredcites →https://doi.org/10.1609/aaai.v36i5.20469openalex-snapshot
Teaching Humans When to Defer to a Classifier via Exemplars
inferredcites →https://doi.org/10.1609/aaai.v37i5.25682openalex-snapshot
Now We’re Talking: Better Deliberation Groups through Submodular Optimization
inferredcites →https://doi.org/10.1609/hcomp.v7i1.5285openalex-snapshot
Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance
inferredcites →https://doi.org/10.18653/v1/2020.acl-main.386openalex-snapshot
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?
inferredcites →https://doi.org/10.18653/v1/2020.acl-main.408openalex-snapshot
ERASER: A Benchmark to Evaluate Rationalized NLP Models
inferredcites →https://doi.org/10.18653/v1/2020.acl-main.491openalex-snapshot
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?
inferredcites →https://doi.org/10.18653/v1/2020.acl-main.647openalex-snapshot
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
inferredcites →https://doi.org/10.18653/v1/2020.findings-emnlp.301openalex-snapshot
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
inferredcites →https://doi.org/10.18653/v1/2023.emnlp-main.615openalex-snapshot
Characterizing Mechanisms for Factual Recall in Language Models
inferredcites →https://doi.org/10.18653/v1/2023.findings-acl.847openalex-snapshot
Discovering Language Model Behaviors with Model-Written Evaluations
inferredcites →https://doi.org/10.18653/v1/2024.findings-emnlp.439openalex-snapshot
On Evaluating Explanation Utility for Human-AI Decision Making in NLP
inferredcites →https://doi.org/10.2139/ssrn.4217679openalex-snapshot
Catastrophic uncertainty and regulatory impact analysis
inferredcites →https://doi.org/10.2190/flhv-k4wa-wpvq-h0ymopenalex-snapshot
Computer Gaming and Interactive Simulations for Learning: A Meta-Analysis
inferredcites →https://doi.org/10.2307/2654376openalex-snapshot
Actor Network Theory and After
inferredcites →https://doi.org/10.23915/distill.00024.001openalex-snapshot
Zoom In: An Introduction to Circuits
inferredcites →https://doi.org/10.3389/fcomp.2023.1117848openalex-snapshot
Explainable AI: roles and stakeholders, desirements and challenges
inferredcites →https://doi.org/10.3389/fpos.2023.1127372openalex-snapshot
Deliberation and polarization: a multi-disciplinary review
inferredcites →https://doi.org/10.4230/lipics.concur.2020.3openalex-snapshot
Agnostic Learning with Unknown Utilities
inferredcites →https://doi.org/10.48550/arxiv.1607.06520openalex-snapshot
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
inferredcites →https://doi.org/10.48550/arxiv.1610.02136openalex-snapshot
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
inferredcites →https://doi.org/10.48550/arxiv.1702.08608openalex-snapshot
Towards A Rigorous Science of Interpretable Machine Learning
inferredcites →https://doi.org/10.48550/arxiv.1703.01365openalex-snapshot
Axiomatic Attribution for Deep Networks
inferredcites →https://doi.org/10.48550/arxiv.1706.03741openalex-snapshot
Deep reinforcement learning from human preferences
inferredcites →https://doi.org/10.48550/arxiv.1711.11279openalex-snapshot
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
inferredcites →https://doi.org/10.48550/arxiv.1911.09005openalex-snapshot
Hard Choices in Artificial Intelligence: Addressing Normative Uncertainty through Sociotechnical Commitments
inferredcites →https://doi.org/10.48550/arxiv.2001.00964openalex-snapshot
Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
inferredcites →https://doi.org/10.48550/arxiv.2001.04335openalex-snapshot
Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society
inferredcites →https://doi.org/10.48550/arxiv.2004.07213openalex-snapshot
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
inferredcites →https://doi.org/10.48550/arxiv.2007.04612openalex-snapshot
Concept Bottleneck Models
inferredcites →https://doi.org/10.48550/arxiv.2012.07805openalex-snapshot
Extracting Training Data from Large Language Models
inferredcites →https://doi.org/10.48550/arxiv.2202.00734openalex-snapshot
Framework for Evaluating Faithfulness of Local Explanations
inferredcites →https://doi.org/10.48550/arxiv.2202.05262openalex-snapshot
Locating and Editing Factual Associations in GPT
inferredcites →https://doi.org/10.48550/arxiv.2203.11147openalex-snapshot
Teaching language models to support answers with verified quotes
inferredcites →https://doi.org/10.48550/arxiv.2204.05862openalex-snapshot
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
inferredcites →https://doi.org/10.48550/arxiv.2204.11966openalex-snapshot
Estimating and Penalizing Induced Preference Shifts in Recommender Systems
inferredcites →https://doi.org/10.48550/arxiv.2206.05862openalex-snapshot
X-Risk Analysis for AI Research
inferredcites →https://doi.org/10.48550/arxiv.2207.04958openalex-snapshot
Documenting Data Production Processes: A Participatory Approach for Data Work
inferredcites →https://doi.org/10.48550/arxiv.2207.05221openalex-snapshot
Language Models (Mostly) Know What They Know
inferredcites →https://doi.org/10.48550/arxiv.2209.00626openalex-snapshot
The Alignment Problem from a Deep Learning Perspective
inferredcites →https://doi.org/10.48550/arxiv.2209.07858openalex-snapshot
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
inferredcites →https://doi.org/10.48550/arxiv.2209.09056openalex-snapshot
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
inferredcites →https://doi.org/10.48550/arxiv.2209.11801openalex-snapshot
Solutions to preference manipulation in recommender systems require knowledge of meta-preferences
inferredcites →https://doi.org/10.48550/arxiv.2210.02667openalex-snapshot
A Human Rights-Based Approach to Responsible AI
inferredcites →https://doi.org/10.48550/arxiv.2211.03540openalex-snapshot
Measuring Progress on Scalable Oversight for Large Language Models
inferredcites →https://doi.org/10.48550/arxiv.2211.13069openalex-snapshot
Cultural Incongruencies in Artificial Intelligence
inferredcites →https://doi.org/10.48550/arxiv.2212.03827openalex-snapshot
Discovering Latent Knowledge in Language Models Without Supervision
inferredcites →https://doi.org/10.48550/arxiv.2212.09251openalex-snapshot
Discovering Language Model Behaviors with Model-Written Evaluations
inferredcites →https://doi.org/10.48550/arxiv.2212.09746openalex-snapshot
Evaluating Human-Language Model Interaction
inferredcites →https://doi.org/10.48550/arxiv.2301.04709openalex-snapshot
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
inferredcites →https://doi.org/10.48550/arxiv.2301.09976openalex-snapshot
Bridging Systems: Open Problems for Countering Destructive Divisiveness across Ranking, Recommenders, and Governance
inferredcites →https://doi.org/10.48550/arxiv.2302.00672openalex-snapshot
'Generative CI' through Collective Response Systems
inferredcites →https://doi.org/10.48550/arxiv.2304.04914openalex-snapshot
Regulatory Markets: The Future of AI Governance
inferredcites →https://doi.org/10.48550/arxiv.2305.02469openalex-snapshot
The System Model and the User Model: Exploring AI Dashboard Design
inferredcites →https://doi.org/10.48550/arxiv.2305.15324openalex-snapshot
Model evaluation for extreme risks
inferredcites →https://doi.org/10.48550/arxiv.2306.11932openalex-snapshot
Opportunities and Risks of LLMs for Scalable Deliberation with Polis
inferredcites →https://doi.org/10.48550/arxiv.2306.13952openalex-snapshot
Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools
inferredcites →https://doi.org/10.48550/arxiv.2307.03718openalex-snapshot
Frontier AI Regulation: Managing Emerging Risks to Public Safety
inferredcites →https://doi.org/10.48550/arxiv.2307.08678openalex-snapshot
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
inferredcites →https://doi.org/10.48550/arxiv.2307.13702openalex-snapshot
Measuring Faithfulness in Chain-of-Thought Reasoning
inferredcites →https://doi.org/10.48550/arxiv.2309.01933openalex-snapshot
Provably safe systems: the only path to controllable AGI
inferredcites →https://doi.org/10.48550/arxiv.2309.05858openalex-snapshot
Uncovering mesa-optimization algorithms in Transformers
inferredcites →https://doi.org/10.48550/arxiv.2310.02238openalex-snapshot
Who's Harry Potter? Approximate Unlearning in LLMs
inferredcites →https://doi.org/10.48550/arxiv.2310.11986openalex-snapshot
Sociotechnical Safety Evaluation of Generative AI Systems
inferredcites →https://doi.org/10.48550/arxiv.2311.02242openalex-snapshot
Democratic Policy Development using Collective Dialogues and AI
inferredcites →https://doi.org/10.48550/arxiv.2311.04354openalex-snapshot
Uncovering Intermediate Variables in Transformers using Circuit Probing
inferredcites →https://doi.org/10.48550/arxiv.2312.14230openalex-snapshot
Views on AI aren't binary -- they're plural
inferredcites →https://doi.org/10.5040/9781474248655.0037openalex-snapshot
The coming technological singularity: How to survive in a post-human era
inferredcites →https://doi.org/10.5210/fm.v27i5.12604openalex-snapshot
Designing recommender systems to depolarize
inferredcites →https://doi.org/10.52202/068431-2766openalex-snapshot
Fine-Tuning Language Models to Find Agreement Among Humans with Diverse Preferences
inferredcites →https://doi.org/10.52202/075280-1328openalex-snapshot
Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
inferredcites →https://doi.org/10.52202/075280-2884openalex-snapshot
LEACE: Perfect linear concept erasure in closed form
inferredcites →https://doi.org/10.52202/075280-2997openalex-snapshot
Toolformer: Language Models Can Teach Themselves to Use Tools
inferredcites →https://doi.org/10.52202/075280-3275openalex-snapshot
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
inferredcites →https://doi.org/10.5281/zenodo.19196502openalex-snapshot
Detecting Performed Alignment in Artificial Systems: The Munafiq Protocol
inferredcites →https://doi.org/10.5860/choice.29-4214openalex-snapshot
Feminism confronts technology
inferredcites →https://doi.org/10.7551/mitpress/7221.001.0001openalex-snapshot
Where the Action Is
Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.