mlsanityData to 7 Oct 2026

Generating Place-Based Compromises Between Two Points of View

arXiv 2604.24536 ↗First posted 27 Apr 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) excel academically but struggle with social intelligence tasks, such as creating good compromises. In this paper, we present methods for generating empathically neutral compromises between two opposing viewpoints. We first compared four different prompt engineering methods using Claude 3 Opus and a dataset of 2,400 contrasting views on shared places. A subset of the gen erated compromises was evaluated for acceptability in a 50-participant study. We found that the best method for generating compromises between two views used external empathic similarity between a compromise and each viewpoint as iterative feedback, outperforming stan dard Chain of Thought (CoT) reasoning. The results indicate that the use of empathic neutrality improves the acceptability of compromises. The dataset of generated compromises was then used to train two smaller foundation models via margin-based alignment of human preferences, improving efficiency and removing the need for empathy estimation during inference.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 70 references that are in the map. First posted on arXiv 27 Apr 2026.

Builds on

38 of 70 references.

References · 38

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  8. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  9. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  10. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  11. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspectivecited by 293
  12. 2023Preference Ranking Optimization for Human Alignmentcited by 283
26 more
  1. 2024Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positivecited by 239
  2. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  3. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  4. 2024Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewardscited by 145
  5. 2020MIME: MIMicking Emotions for Empathetic Response Generationcited by 114
  6. 2021CEM: Commonsense-aware Empathetic Response Generationcited by 89
  7. 2024Noise Contrastive Alignment of Language Models with Explicit Rewardscited by 85
  8. 2023Aligning Large Language Models with Human Preferences through Representation Engineeringcited by 71
  9. 2024Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuningcited by 71
  10. 2024Robust Preference Optimization through Reward Model Distillationcited by 67
  11. 2023Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmarkcited by 62
  12. 2018Diversity in Machine Learningcited by 48
  13. 2024Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Promptscited by 36
  14. 2024Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilitiescited by 31
  15. 2023Safer-Instruct: Aligning Language Models with Automated Preference Datacited by 27
  16. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 25
  17. 2021EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Predictioncited by 17
  18. 2023Modeling Empathic Similarity in Personal Narrativescited by 14
  19. 2023CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignmentcited by 13
  20. 2024Robots in the Middle: Evaluating LLMs in Dispute Resolutioncited by 13
  21. 2024Academically intelligent LLMs are not necessarily socially intelligentcited by 12
  22. 2024Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversationscited by 9
  23. 2023Efficient Domain Adaptation of Sentence Embeddings Using Adapterscited by 6
  24. 2024TODO: Enhancing LLM Alignment with Ternary Preferencescited by 5
  25. 2024Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerationscited by 3
  26. 2024Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussionscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization
  2. 2024Quantitative Assessment of Intersectional Empathetic Bias and Understanding
  3. 2026Hidden Consensus:Preference-Validity Compression in Human Feedback
  4. 2026Misaligned by Reward: Socially Undesirable Preferences in LLMs
  5. 2024Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses
  6. 2025EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
  7. 2026The Fragility Of Moral Judgment In Large Language Models
  8. 2026Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning