LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
hub
So- cial choice for ai alignment: Dealing with diverse human feedback
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
An exact single-voter manipulation oracle turns LLM strategic voting under plurality, Borda, approval, IRV, and Copeland into a fully labeled, reproducible benchmark with calibration baselines.
PEBS applies Morris-James-Stein empirical-Bayes shrinkage to per-rater affine calibrators in RLHF, cutting within-user held-out RMSE by 8.58% on PRISM and 9.66% on PluriHarms versus pooled baselines.
Empirical study of Malaysian preference judgments finds that 79% of prompts have multiple majority-supported responses discarded by single-winner aggregation, indicating measurement of argmax rather than plural alignment.
Emergence World is a model-agnostic multi-agent simulation platform integrating live data, 120+ tools, persistent memory, and democratic governance, illustrated by a 15-day study showing divergent outcomes across five LLM models.
A novel online weighted aggregation mechanism for truthful preference feedback in mobile crowdsourcing achieves sublinear regret O(sqrt(T)) and truthfulness in a dynamic Bayesian game, with an extension for limited feedback per slot.
Maximizing reachability in k-path temporal graphs via budgeted shifts is FPT when parameterized by k and b together or by k alone, but intractable in most other parameterizations with matching XP algorithms.
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
The Hidden Utility Bandit (HUB) framework models teacher heterogeneity in reward learning and supports active teacher selection algorithms that outperform baselines in paper recommendation and COVID-19 vaccine testing domains.
ICM-inferred examples achieve gold-label performance across alignment benchmarks and generalize better when coherence is high even at fixed accuracy.
A tradeoff model shows generative AI can reduce bias against diverse preferences by strategically eliciting information instead of always inferring from majority patterns.
AI value alignment is reconceptualized as a pluralistic governance problem arising along three axes—objectives, information, and principals—making it inherently context-dependent and unsolvable by technical design alone.
AI alignment to principles requires context-sensitive interpretive judgments, as substantial preference data involves unresolved conflicts, creating gaps between corpus-induced and deployment-induced evaluations.
An autonomy-qualified Second Welfare Theorem is stated for post-AGI economies under the joint conditions of convexity, stable moral status, non-fungible rights, welfare selection, non-manipulation, governed self-modification, and verification.
citing papers explorer
-
Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance
LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
-
Three Models of RLHF Annotation: Extension, Evidence, and Authority
RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
-
Do Large Language Model Voters Strategize? An Oracle-Based Benchmark for Manipulation under Voting Rules
An exact single-voter manipulation oracle turns LLM strategic voting under plurality, Borda, approval, IRV, and Copeland into a fully labeled, reproducible benchmark with calibration baselines.
-
PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration
PEBS applies Morris-James-Stein empirical-Bayes shrinkage to per-rater affine calibrators in RLHF, cutting within-user held-out RMSE by 8.58% on PRISM and 9.66% on PluriHarms versus pooled baselines.
-
Hidden Consensus:Preference-Validity Compression in Human Feedback
Empirical study of Malaysian preference judgments finds that 79% of prompts have multiple majority-supported responses discarded by single-winner aggregation, indicating measurement of argmax rather than plural alignment.
-
Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy
Emergence World is a model-agnostic multi-agent simulation platform integrating live data, 120+ tools, persistent memory, and democratic governance, illustrated by a 15-day study showing divergent outcomes across five LLM models.
-
Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing
A novel online weighted aggregation mechanism for truthful preference feedback in mobile crowdsourcing achieves sublinear regret O(sqrt(T)) and truthfulness in a dynamic Bayesian game, with an extension for limited feedback per slot.
-
Maximizing Reachability via Shifting of Temporal Paths
Maximizing reachability in k-path temporal graphs via budgeted shifts is FPT when parameterized by k and b together or by k alone, but intractable in most other parameterizations with matching XP algorithms.
-
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
-
Active teacher selection for reward learning
The Hidden Utility Bandit (HUB) framework models teacher heterogeneity in reward learning and supports active teacher selection algorithms that outperform baselines in paper recommendation and COVID-19 vaccine testing domains.
-
Coherence Maximization Improves Pluralistic Alignment
ICM-inferred examples achieve gold-label performance across alignment benchmarks and generalize better when coherence is high even at fixed accuracy.
-
When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
A tradeoff model shows generative AI can reduce bias against diverse preferences by strategically eliciting information instead of always inferring from majority patterns.
-
Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
AI value alignment is reconceptualized as a pluralistic governance problem arising along three axes—objectives, information, and principals—making it inherently context-dependent and unsolvable by technical design alone.
-
Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment
AI alignment to principles requires context-sensitive interpretive judgments, as substantial preference data involves unresolved conflicts, creating gaps between corpus-induced and deployment-induced evaluations.
-
Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics
An autonomy-qualified Second Welfare Theorem is stated for post-AGI economies under the joint conditions of convexity, stable moral status, non-fungible rights, welfare selection, non-manipulation, governed self-modification, and verification.