# Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements

arXiv: https://arxiv.org/abs/2402.10614 · HTML: https://mlsanity.com/paper/2402.10614/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 67 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 30 of 52)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)

## Built on by (most cited first, 30 of 34)

- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [Aligning to Thousands of Preferences via System Message Generalization](https://mlsanity.com/paper/2405.17977/) (2024)
- [ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2503.09501/) (2025)
- [SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models](https://mlsanity.com/paper/2410.18927/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2411.00053/) (2024)
- [Multiple LLM Agents Debate for Equitable Cultural Alignment](https://mlsanity.com/paper/2505.24671/) (2025)
- [Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook](https://mlsanity.com/paper/2602.14299/) (2026)
- [From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs](https://mlsanity.com/paper/2502.17701/) (2025)
- [RuleR: Improving LLM Controllability by Rule-based Data Recycling](https://mlsanity.com/paper/2406.15938/) (2024)
- [Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning](https://mlsanity.com/paper/2405.13326/) (2024)
- [SGIC: A Self-Guided Iterative Calibration Framework for RAG](https://mlsanity.com/paper/2506.16172/) (2025)
- [Computational Hermeneutics: Evaluating generative AI as a cultural technology](https://mlsanity.com/paper/2604.16403/) (2026)
- [Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models](https://mlsanity.com/paper/2507.07484/) (2025)
- [Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents](https://mlsanity.com/paper/2507.19090/) (2025)
- [Interactive Learning for LLM Reasoning](https://mlsanity.com/paper/2509.26306/) (2025)
- [Multi-Objective Linguistic Control of Large Language Models](https://mlsanity.com/paper/2406.16229/) (2024)
- [Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment](https://mlsanity.com/paper/2412.20834/) (2024)
- [MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections](https://mlsanity.com/paper/2502.00322/) (2025)
- [Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals](https://mlsanity.com/paper/2404.13885/) (2024)
- [Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL](https://mlsanity.com/paper/2503.03654/) (2025)
- [Revealing Political Bias in LLMs through Structured Multi-Agent Debate](https://mlsanity.com/paper/2506.11825/) (2025)
- [MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement](https://mlsanity.com/paper/2512.07898/) (2025)
- [UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality](https://mlsanity.com/paper/2503.10669/) (2025)
- [Neurosymbolic Learning for Inference-Time Argumentation](https://mlsanity.com/paper/2605.20098/) (2026)
- [Stance-Driven Multimodal Controlled Statement Generation: New Dataset and Task](https://mlsanity.com/paper/2504.03295/) (2025)
- [Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents](https://mlsanity.com/paper/2604.22452/) (2026)
- [The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2606.03032/) (2026)
- [ForensicsData: A Digital Forensics Dataset for Large Language Models](https://mlsanity.com/paper/2509.05331/) (2025)

## Abstract (arXiv)

Making LLMs speak for different, especially minority groups of people, and generate statements supporting their diverse or even controversial perspectives is critical to creating an inclusive environment. However, existing LLMs lack sufficient controllability to the stance of their generated content, which often contains inconsistent, neutral, or biased statements. In this paper, we improve the controllability of LLMs in generating statements supporting an argument the user defined in the prompt. We find that multi-round debates between two LLMs with opposite stances generate higher-quality and more salient statements for each, which are important training data to improve the controllability of LLMs. Motivated by this, we develop a novel debate & tuning (DEBATUNE) pipeline finetuning LLMs to generate the statements obtained via debate. To examine DEBATUNE, we curate the largest dataset of debate topics so far, which covers 710 controversial topics and corresponding arguments for each topic. Evaluations by the GPT-4 judge with a novel controversy controllability metric show that LLMs' capability of generating diverse perspectives is significantly improved by DEBATUNE. Moreover, such controllability can be generalized to unseen topics, generating high-quality statements supporting controversial arguments.