# Computing Voting Rules with Improvement Feedback

arXiv: https://arxiv.org/abs/2502.12542 · HTML: https://mlsanity.com/paper/2502.12542/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language](https://mlsanity.com/paper/2311.14543/) (2023)
- [Trajectory Improvement and Reward Learning from Comparative Language Feedback](https://mlsanity.com/paper/2410.06401/) (2024)
- [Sample Complexity for Winner Prediction in Elections](https://mlsanity.com/paper/1502.04354/) (2015)
- [Computing Voting Rules with Elicited Incomplete Votes](https://mlsanity.com/paper/2402.11104/) (2024)
- [Comparing Election Methods Where Each Voter Ranks Only Few Candidates](https://mlsanity.com/paper/1901.10848/) (2019)

## Abstract (arXiv)

Aggregating preferences under incomplete or constrained feedback is a fundamental problem in social choice and related domains. While prior work has established strong impossibility results for pairwise comparisons, this paper extends the inquiry to improvement feedback, where voters express incremental adjustments rather than complete preferences. We provide a complete characterization of the positional scoring rules that can be computed given improvement feedback. Interestingly, while plurality is learnable under improvement feedback--unlike with pairwise feedback--strong impossibility results persist for many other positional scoring rules. Furthermore, we show that improvement feedback, unlike pairwise feedback, does not suffice for the computation of any Condorcet-consistent rule. We complement our theoretical findings with experimental results, providing further insights into the practical implications of improvement feedback for preference aggregation.