Generating Fair Consensus Statements with Social Choice on Token-Level MDPs

• URL: http://arxiv.org/abs/2510.14106v1
• Date: Wed, 15 Oct 2025 21:23:18 GMT
• Title: Generating Fair Consensus Statements with Social Choice on Token-Level MDPs
• Authors: Carter Blair, Kate Larson,
• Abstract summary: We model the task as a multi-objective, token-level Markov Decision Process (MDP)<n> Token-level rewards for each agent are derived from their policy (e.g., a personalized language model)<n>This approach utilizes the finding that such policies implicitly define optimal Q-functions, providing a principled way to quantify rewards at each generation step without a value function.
• Score: 7.5036512760759715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current frameworks for consensus statement generation with large language models lack the inherent structure needed to provide provable fairness guarantees when aggregating diverse free-form opinions. We model the task as a multi-objective, token-level Markov Decision Process (MDP), where each objective corresponds to an agent's preference. Token-level rewards for each agent are derived from their policy (e.g., a personalized language model). This approach utilizes the finding that such policies implicitly define optimal Q-functions, providing a principled way to quantify rewards at each generation step without a value function (Rafailov et al., 2024). This MDP formulation creates a formal structure amenable to analysis using principles from social choice theory. We propose two approaches grounded in social choice theory. First, we propose a stochastic generation policy guaranteed to be in the ex-ante core, extending core stability concepts from voting theory to text generation. This policy is derived from an underlying distribution over complete statements that maximizes proportional fairness (Nash Welfare). Second, for generating a single statement, we target the maximization of egalitarian welfare using search algorithms within the MDP framework. Empirically, experiments using language models to instantiate agent policies show that search guided by the egalitarian objective generates consensus statements with improved worst-case agent alignment compared to baseline methods, including the Habermas Machine (Tessler et al., 2024).

Related papers

• Owen-Shapley Policy Optimization (OSPO): A Principled RL Algorithm for Generative Search LLMs [12.75200353208858]
  Owen-Shapley Policy Optimization (OSPO) is a framework that redistributes sequence-level advantages based on tokens' marginal contributions to outcomes.<n>Unlike value-model-based methods requiring additional computation, OSPO employs potential-based reward shaping via Shapley-Owen attributions to assign segment-level credit.<n> Experiments on Amazon ESCI and H&M Fashion datasets show consistent gains over baselines.
  arXiv  Detail & Related papers  (2026-01-13T10:17:46Z)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• On Dynamic Programming Theory for Leader-Follower Stochastic Games [10.079626733116612]
  Leader-follower general-sum games (LF-GSSGs) model sequential decision-making under asymmetric commitment.<n>This paper introduces a dynamic programming framework that applies Bellman over credible sets-state abstractions.
  arXiv  Detail & Related papers  (2025-12-05T12:23:56Z)
• Best-Effort Policies for Robust Markov Decision Processes [69.60742680559788]
  We study the common generalization of Markov decision processes (MDPs) with sets of transition probabilities, known as robust MDPs (RMDPs)<n>We call such a policy an optimal robust best-effort (ORBE) policy.<n>We prove that ORBE policies always exist, characterize their structure, and present an algorithm to compute them with a small overhead compared to standard robust value iteration.
  arXiv  Detail & Related papers  (2025-08-11T09:18:34Z)
• hyperFA*IR: A hypergeometric approach to fair rankings with finite candidate pool [0.0]
  We present hyperFA*IR, a framework for assessing and enforcing fairness in rankings drawn from a finite set of candidates.<n>It relies on a generative process based on the hypergeometric distribution, which models real-world scenarios by sampling without replacement from fixed group sizes.<n>We also propose a Monte Carlo-based algorithm that efficiently detects unfair rankings by avoiding computationally expensive parameter tuning.
  arXiv  Detail & Related papers  (2025-06-17T09:45:08Z)
• QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA [46.65999744568314]
  We introduce QA-LIGN, which decomposes monolithic rewards into interpretable principle-specific evaluations.<n>Applying to uncensored Llama-3.1-8B-Instruct, QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate.
  arXiv  Detail & Related papers  (2025-06-09T18:24:57Z)
• Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models [20.810300785340072]
  Conformal Prediction with Query Oracle (CPQ) is a framework characterizing the optimal interplay between these objectives.<n>Our algorithm is built on two core principles: one governs the optimal query policy, and the other defines the optimal mapping from queried samples to prediction sets.
  arXiv  Detail & Related papers  (2025-06-05T18:26:14Z)
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time [52.230936493691985]
  We propose SITAlign, an inference framework that addresses the multifaceted nature of alignment by maximizing a primary objective while satisfying threshold-based constraints on secondary criteria.<n>We provide theoretical insights by deriving sub-optimality bounds of our satisficing based inference alignment approach.
  arXiv  Detail & Related papers  (2025-05-29T17:56:05Z)
• Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach [2.8626097661711394]
  Reinforcement Learning from Human Feedback has achieved notable success in steering models, but is complex and can be unstable.<n>Recent approaches such as Direct Preference Optimization (DPO) simplify preference-based fine-tuning but may introduce bias or trade-off certain objectives.<n>We propose a Group Relative Policy Optimization framework with a multi-label reward regression model to achieve safe and aligned language generation.
  arXiv  Detail & Related papers  (2025-03-26T05:50:33Z)
• Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling [84.00480999255628]
  Reinforcement Learning algorithms for safety alignment of Large Language Models (LLMs) encounter the challenge of distribution shift.<n>Current approaches typically address this issue through online sampling from the target policy.<n>We propose a new framework that leverages the model's intrinsic safety judgment capability to extract reward signals.
  arXiv  Detail & Related papers  (2025-03-13T06:40:34Z)
• Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model [14.480267340831542]
  Structure-aware Planning with an Accurate World Model (SWAP)<n>SWAP integrates structured knowledge representation with learned planning.<n>We evaluate SWAP across diverse reasoning-intensive benchmarks including math reasoning, logical reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2024-10-04T04:23:36Z)
• Personalized Reinforcement Learning with a Budget of Policies [9.846353643883443]
  Personalization in machine learning (ML) tailors models' decisions to the individual characteristics of users. We propose a novel framework termed represented Markov Decision Processes (r-MDPs) that is designed to balance the need for personalization with the regulatory constraints. In an r-MDP, we cater to a diverse user population, each with unique preferences, through interaction with a small set of representative policies. We develop two deep reinforcement learning algorithms that efficiently solve r-MDPs.
  arXiv  Detail & Related papers  (2024-01-12T11:27:55Z)
• Interpretable Reinforcement Learning with Multilevel Subgoal Discovery [77.34726150561087]
  We propose a novel Reinforcement Learning model for discrete environments. In the model, an agent learns information about environment in the form of probabilistic rules. No reward function is required for learning; an agent only needs to be given a primary goal to achieve.
  arXiv  Detail & Related papers  (2022-02-15T14:04:44Z)
• Implicit Distributional Reinforcement Learning [61.166030238490634]
  implicit distributional actor-critic (IDAC) built on two deep generator networks (DGNs) Semi-implicit actor (SIA) powered by a flexible policy distribution. We observe IDAC outperforms state-of-the-art algorithms on representative OpenAI Gym environments.
  arXiv  Detail & Related papers  (2020-07-13T02:52:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.