mlsanityData to 14 Oct 2026

SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs

arXiv 2504.12633 ↗First posted 17 Apr 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) not only have solved complex reasoning problems but also exhibit remarkable performance in tasks that require subjective decision making. Existing studies suggest that LLM generations can be subjectively grounded to some extent, yet exploring whether LLMs can account for individual-level subjectivity has not been sufficiently studied. In this paper, we characterize subjectivity of individuals on social media and infer their moral judgments using LLMs. We propose a framework, SOLAR (Subjective Ground with Value Abstraction), that observes value conflicts and trade-offs in the user-generated texts to better represent subjective ground of individuals. Empirical results show that our framework improves overall inference results as well as performance on controversial situations. Additionally, we qualitatively show that SOLAR provides explanations about individuals' value preferences, which can further account for their judgments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 61 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

34 of 61 references.

References · 34

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  9. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  10. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  12. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
22 more
  1. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  3. 2023Whose Opinions Do Language Models Reflect?cited by 773
  4. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  5. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  6. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  7. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  8. 2024Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooMcited by 78
  9. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  10. 2023Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactionscited by 70
  11. 2023Can Large Language Models Understand Real-World Complex Instructions?cited by 69
  12. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  13. 2024UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systemscited by 38
  14. 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learningcited by 29
  15. 2025Value Profiles for Encoding Human Variationcited by 29
  16. 2022Unifying Data Perspectivism and Personalization: An Application to Social Normscited by 22
  17. 2023Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Taskscited by 21
  18. 2023Do Differences in Values Influence Disagreements in Online Discussions?cited by 15
  19. 2023IAG: Induction-Augmented Generation Framework for Answering Reasoning Questionscited by 15
  20. 2023Large Language Models as Source Planner for Personalized Knowledge-grounded Dialoguecited by 6
  21. 2023"We Demand Justice!": Towards Social Context Grounding of Political Textscited by 4
  22. 2022Towards Explaining Subjective Ground of Individuals on Social Mediacited by 2

Built on by

Not cited yet.