Challenge: Recent approaches to align LLMs with diverse human values are based on static linear scalarization or rigid gradient projection . however, these approaches often sacrifice potential global Pareto improvements to avoid transient local trade-offs.
Approach: They propose a game-theoretic framework that reimagines alignment as a dynamic negotiation process.
Outcome: The proposed framework breaks the deadlock between static linear scalarization and rigid gradient projection . it allows the model to escape local degradation and explore the distal Pareto-optimal frontier .

Similar Papers

Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to optimize large language models with human preferences suffer from preference conflicts in the data.
Approach: They propose to construct Pareto-optimal responses to resolve preference conflicts by using a self-improving DPO framework that enables LLMs to self-generate and select Paret-optimized responses.
Outcome: The proposed framework achieves superior Pareto Front performance over baselines on two datasets.
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences.
Approach: They propose a novel algorithm that uses multiple-gradient descent to optimize LLMs with diverse preferences to maximize trade-offs between objectives.
Outcome: The proposed approach incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user’s specific needs.
MERIT Feedback Elicits Better Bargaining in LLM Negotiators (2026.acl-long)

Copied to clipboard

Challenge: Empirical results indicate that baseline LLM strategies diverge from human preferences, while our mechanism substantially improves negotiation performance.
Approach: They propose a utility feedback centric framework that measures human-aligned, economically grounded metrics that implicitly measure how well the negotiation aligns with human preference.
Outcome: The proposed framework significantly improves negotiation performance, yielding deeper strategic behavior and stronger opponent awareness.
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment (2024.emnlp-main)

Copied to clipboard

Challenge: Existing algorithms for achieving optimal alignment are mostly unidirectional . a recent study suggests that large language models can be ground with evident preferences .
Approach: They propose to ground large language models with evident preferences . they propose to use controllable preference optimization to specify different objectives .
Outcome: The proposed models can provide responses that match various preferences among the ”3H” desiderata.
PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) depend on vast amounts of text data sourced from the Internet for their training.
Approach: They propose a new alignment paradigm that reformulates risky queries into highly relevant yet harmless ones before feeding them into LLMs.
Outcome: The proposed approach eliminates the high costs of training base LLMs and achieves a promising balance of harmlessness and helpfulness.
Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for training large language models require additional annotations to adjust to shifted distributions.
Approach: They propose an algorithm that allows LLMs and reward models to update alternatively via a min-max game to improve their alignment.
Outcome: The proposed framework improves existing alignment baselines in terms of LLM helpfulness and harmlessness.
A Grounded Preference Model for LLM Alignment (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) suffer from factual inconsistency and hallucination despite recent advances . training a preference model requires substantial human annotation, which is expensive and labor-intensive.
Approach: They propose to generate synthetic grounded preference data and train a Grounded Preference Model to assess the overall quality of grounded responses.
Outcome: The proposed model can generate much better grounded responses as judged by GPT4 and achieves the TRUE faithfulness Benchmark.
Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to align LLMs with diverse human values rely on ground-truth scores . existing approaches implicitly approximate an average-user preference, thereby failing to capture heterogeneity of human values or accommodate conflicting user needs.
Approach: They propose a framework that transforms passive reward dependency into an intrinsic adaptive sensing capability.
Outcome: The proposed framework outperforms state-of-the-art models in multiple model scales and improves preference alignment.
The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems (2025.emnlp-main)

Copied to clipboard

Challenge: Conventional LLM-based MAS rely on explicit coordination, e.g., prompts or voting, risking premature homogenization.
Approach: They propose to preserve partial diversity by combining in-context learning with explicit coordination to form consensus in dynamic environments.
Outcome: The proposed model outperforms explicit consensus models on three scenarios showing that partial deviation from group norms boosts exploration, robustness, and performance.
Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown that acquiring human preferences by comparing generations is not effective for large language models.
Approach: They propose a preference optimization objective that elicits preferences jointly over the instruction-response pairs.
Outcome: The proposed approach outperforms prior preference optimizations by 5.2% and 3.3% in summarization and open-ended dialogue datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations