# Consensus vs. Dissent: Dynamic LLM Modeling of Subjective Preferences in Group Recommenders

arXiv: https://arxiv.org/abs/2607.10235 · HTML: https://mlsanity.com/paper/2607.10235/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 53 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences](https://mlsanity.com/paper/2307.14225/) (2023)
- [LLaRA: Large Language-Recommendation Assistant](https://mlsanity.com/paper/2312.02445/) (2023)
- [Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System](https://mlsanity.com/paper/2404.11343/) (2024)
- [A Comprehensive Evaluation of Cognitive Biases in LLMs](https://mlsanity.com/paper/2410.15413/) (2024)
- [Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation](https://mlsanity.com/paper/2109.04200/) (2021)
- [Fairness in Recommender Systems: Research Landscape and Future Directions](https://mlsanity.com/paper/2205.11127/) (2022)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations](https://mlsanity.com/paper/2306.17256/) (2023)
- [On Explaining Recommendations with Large Language Models: A Review](https://mlsanity.com/paper/2411.19576/) (2024)
- [Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systems](https://mlsanity.com/paper/2404.11773/) (2024)
- [A Matter of Perspective(s): Contrasting Human and LLM Argumentation in Subjective Decision-Making on Subtle Sexism](https://mlsanity.com/paper/2502.14052/) (2025)
- [Stream-Based Monitoring of Algorithmic Fairness](https://mlsanity.com/paper/2501.18331/) (2025)
- [With Friends Like These, Who Needs Explanations? Evaluating User Understanding of Group Recommendations](https://mlsanity.com/paper/2505.04273/) (2025)
- [The Pitfalls of Growing Group Complexity: LLMs and Social Choice-Based Aggregation for Group Recommendations](https://mlsanity.com/paper/2505.05016/) (2025)
- [Consistent Explainers or Unreliable Narrators? Understanding LLM-generated Group Recommendations](https://mlsanity.com/paper/2507.13705/) (2025)

## Abstract (arXiv)

Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of fairness, satisfaction, and consensus. We do this by fine-tuning Large Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the one that maximizes these predicted human-like evaluations. We further validate these suggestions in a user study (n=284) and find that our methodology achieved the highest scores for satisfaction and group consensus. Furthermore, we find that LLM judgments are most aligned with human perceptions of fairness, satisfaction and consensus when we also consider interaction effects between our LLM-based method and group configuration (e.g., minority or coalition). These findings give further support for dynamically adapting aggregation strategies to specific within-group preference distributions, and highlight the advantage of using LLMs for an adaptation that is aligned with subjective human judgments.