GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare

• URL: http://arxiv.org/abs/2510.08872v3
• Date: Mon, 03 Nov 2025 18:54:17 GMT
• Title: GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare
• Authors: Siqi Zhu, David Zhang, Pedro Cisneros-Velarde, Jiaxuan You,
• Abstract summary: We propose an alignment framework that integrates game-theoretic decision making into both reasoning and training.<n>We show that GTAlign substantially improves reasoning efficiency, answer quality, and social welfare compared to baselines.
• Score: 34.11305361948566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional alignment practices typically assume that maximizing model reward also maximizes user welfare, but this assumption frequently fails in practice: models may over-clarify or generate overly verbose reasoning when users prefer concise answers. Such behaviors resemble the prisoner's dilemma, where individually rational choices lead to socially suboptimal outcomes. The fundamental challenge is the lack of a principled decision making mechanism that mutually benefits both the LLM and the user. We propose Game-Theoretic Alignment (GTAlign), an alignment framework that integrates game-theoretic decision making into both reasoning and training. During reasoning, the model explicitly treats user-LLM interaction as a strategic game: it constructs payoff matrices within its reasoning chain to estimate welfare for both itself and the user, and then selects actions that are mutually beneficial. During training, we introduce a social welfare reward that reinforces cooperative responses, aligning model behavior with socially efficient outcomes. In addition, we introduce an inference technique that leverages game-theoretic reasoning to dynamically adapt LLM's response when pricing policies of LLM service change. Extensive experiments demonstrate that GTAlign substantially improves reasoning efficiency, answer quality, and social welfare compared to baselines across diverse tasks. The code is available at https://github.com/ulab-uiuc/GTAlign .

Related papers

• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization [62.07990937720985]
  Dimension-level Reward Model (DRM) is a new supervision framework for Large Language Models.<n>DRM evaluates the quality of a reasoning process along three fundamental, complementary, and interpretable dimensions.<n> Experimental results show that DRM provides effective supervision signals, guides the optimization of LLMs and enhances their reasoning ability.
  arXiv  Detail & Related papers  (2025-10-13T14:29:15Z)
• Aligning Large Language Models via Fully Self-Synthetic Data [20.05693955243206]
  Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets.<n>In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment.<n>Experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval2.0.
  arXiv  Detail & Related papers  (2025-10-08T05:07:45Z)
• Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare [87.06241096619112]
  Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare.<n>We introduce the Social Welfare Function Benchmark, a dynamic simulation environment where an LLM acts as a sovereign allocator.<n>We evaluate 20 state-of-the-art LLMs and present the first leaderboard for social welfare allocation.
  arXiv  Detail & Related papers  (2025-10-01T17:52:31Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• Post-Training Large Language Models via Reinforcement Learning from Self-Feedback [3.73824942136665]
  Large Language Models (LLMs) often produce plausible but poorly-calibrated answers.<n>We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the model's own confidence as an intrinsic reward.
  arXiv  Detail & Related papers  (2025-07-29T15:46:26Z)
• Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation [9.282278040339138]
  $textbfR2Rec$ is a reasoning-enhanced recommendation framework.<n>It samples interaction chains from the user-item graph and converts them into structured interaction-of-thoughts.
  arXiv  Detail & Related papers  (2025-06-05T14:16:44Z)
• Improving LLM General Preference Alignment via Optimistic Online Mirror Descent [57.622821649679786]
  Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences.<n>In this paper, we drop the Bradley-Terry (BT) model assumption and study LLM alignment under general preferences, formulated as a two-player game.<n>We show that our approach achieves an $O(T-1)$ bound on the duality gap, improving upon the previous $O(T-1/2)$ result.
  arXiv  Detail & Related papers  (2025-02-24T05:24:52Z)
• Approximating Human Strategic Reasoning with LLM-Enhanced Recursive Reasoners Leveraging Multi-agent Hypergames [3.5083201638203154]
  We implement a role-based multi-agent strategic interaction framework tailored to sophisticated reasoners.<n>We use one-shot, 2-player beauty contests to evaluate the reasoning capabilities of the latest LLMs.<n>Our experiments show that artificial reasoners can outperform the baseline model in terms of both approximating human behaviour and reaching the optimal solution.
  arXiv  Detail & Related papers  (2025-02-11T10:37:20Z)
• SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization [70.11167263638562]
  Social relation reasoning aims to identify relation categories such as friends, spouses, and colleagues from images. We first present a simple yet well-crafted framework named name, which combines the perception capability of Vision Foundation Models (VFMs) and the reasoning capability of Large Language Models (LLMs) within a modular framework.
  arXiv  Detail & Related papers  (2024-10-28T18:10:26Z)
• Do LLM Agents Exhibit Social Behavior? [5.094340963261968]
  State-Understanding-Value-Action (SUVA) is a framework to systematically analyze responses in social contexts. It assesses social behavior through both their final decisions and the response generation processes leading to those decisions. We demonstrate that utterance-based reasoning reliably predicts LLMs' final actions.
  arXiv  Detail & Related papers  (2023-12-23T08:46:53Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
  This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision. We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
  arXiv  Detail & Related papers  (2023-10-09T17:56:53Z)

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.