# ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making

arXiv: https://arxiv.org/abs/2602.19458 · HTML: https://mlsanity.com/paper/2602.19458/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 30 of 34)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [Top2Vec: Distributed Representations of Topics](https://mlsanity.com/paper/2008.09470/) (2020)
- [Learning to Complement Humans](https://mlsanity.com/paper/2005.00582/) (2020)
- [OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling](https://mlsanity.com/paper/2506.20512/) (2025)
- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [The Algorithmic Automation Problem: Prediction, Triage, and Human Effort](https://mlsanity.com/paper/1903.12220/) (2019)
- [DICES Dataset: Diversity in Conversational AI Evaluation for Safety](https://mlsanity.com/paper/2306.11247/) (2023)
- [Discovering Discrete Latent Topics with Neural Variational Inference](https://mlsanity.com/paper/1706.00359/) (2017)
- [Differentiable Learning Under Triage](https://mlsanity.com/paper/2103.08902/) (2021)
- [Towards Unbiased and Accurate Deferral to Multiple Experts](https://mlsanity.com/paper/2102.13004/) (2021)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Improving Expert Predictions with Conformal Prediction](https://mlsanity.com/paper/2201.12006/) (2022)
- [Role of Human-AI Interaction in Selective Prediction](https://mlsanity.com/paper/2112.06751/) (2021)
- [A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making](https://mlsanity.com/paper/2205.05126/) (2022)
- [Human-Aligned Calibration for AI-Assisted Decision Making](https://mlsanity.com/paper/2306.00074/) (2023)
- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)
- [When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming](https://mlsanity.com/paper/2306.04930/) (2023)
- [Towards Human-AI Complementarity with Prediction Sets](https://mlsanity.com/paper/2405.17544/) (2024)
- [A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementarity](https://mlsanity.com/paper/2204.10806/) (2022)
- [Explaining Datasets in Words: Statistical Models with Natural Language Parameters](https://mlsanity.com/paper/2409.08466/) (2024)
- [Effective Human-AI Teams via Learned Natural Language Rules and Onboarding](https://mlsanity.com/paper/2311.01007/) (2023)
- [Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservables](https://mlsanity.com/paper/2207.13834/) (2022)
- [On the Effect of Information Asymmetry in Human-AI Teams](https://mlsanity.com/paper/2205.01467/) (2022)

## Built on by (most cited first, 2 of 2)

- [Algorithmic Feature Highlighting for Human-AI Decision-Making](https://mlsanity.com/paper/2604.22236/) (2026)
- [Calibrating LLM Explanations to Human Decisions with Reinforcement Learning](https://mlsanity.com/paper/2610.17306/) (2026)

## Abstract (arXiv)

Multi-agent decision pipelines can outperform single agent workflows when complementarity holds, i.e., different agents bring unique information to the table to inform a final decision. We propose ComplLLM, a post-training framework based on decision theory that fine-tunes a decision-assistant LLM using complementary information as reward to output signals that complement existing agent decisions. We validate ComplLLM on synthetic and real-world tasks involving domain experts, demonstrating how the approach recovers known complementary information and produces plausible explanations of complementary signals to support downstream decision-makers.