# Tell Me Why: Incentivizing Explanations

arXiv: https://arxiv.org/abs/2502.13410 · HTML: https://mlsanity.com/paper/2502.13410/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 46 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (2024)
- [Debate Helps Supervise Unreliable Experts](https://mlsanity.com/paper/2311.08702/) (2023)
- [Are You Smarter Than a Random Expert? The Robust Aggregation of Substitutable Signals](https://mlsanity.com/paper/2111.03153/) (2021)
- [Elicitation for Aggregation](https://mlsanity.com/paper/1410.0375/) (2014)
- [Bayesian Decision Making in Groups is Hard](https://mlsanity.com/paper/1705.04770/) (2017)
- [Learning of Optimal Forecast Aggregation in Partial Evidence Environments](https://mlsanity.com/paper/1802.07107/) (2018)
- [False Consensus, Information Theory, and Prediction Markets](https://mlsanity.com/paper/2206.02993/) (2022)
- [Combining and Extremizing Real-Valued Forecasts](https://mlsanity.com/paper/1506.06405/) (2015)
- [Partial Information Framework: Model-Based Aggregation of Estimates from Diverse Information Sources](https://mlsanity.com/paper/1505.06472/) (2015)
- [Aggregative Efficiency of Bayesian Learning in Networks](https://mlsanity.com/paper/1911.10116/) (2019)
- [Self-Resolving Prediction Markets for Unverifiable Outcomes](https://mlsanity.com/paper/2306.04305/) (2023)

## Built on by (most cited first, 1 of 1)

- [Collective intelligence in science: direct elicitation of diverse information from experts with unknown information structure](https://mlsanity.com/paper/2601.14047/) (2026)

## Abstract (arXiv)

Common sense suggests that when individuals explain why they believe something, we can arrive at more accurate conclusions than when they simply state what they believe. Yet, there is no known mechanism that provides incentives to elicit explanations for beliefs from agents. This likely stems from the fact that standard Bayesian models make assumptions (like conditional independence of signals) that preempt the need for explanations, in order to show efficient information aggregation. A natural justification for the value of explanations is that agents' beliefs tend to be drawn from overlapping sources of information, so agents' belief reports do not reveal all that needs to be known. Indeed, this work argues that rationales-explanations of an agent's private information-lead to more efficient aggregation by allowing agents to efficiently identify what information they share and what information is new. Building on this model of rationales, we present a novel 'deliberation mechanism' to elicit rationales from agents in which truthful reporting of beliefs and rationales is a perfect Bayesian equilibrium.