# Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenders

arXiv: https://arxiv.org/abs/2308.12256 · HTML: https://mlsanity.com/paper/2308.12256/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 23 Aug 2023.

## Builds on (most cited first, 11 of 11)

- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Top-K Off-Policy Correction for a REINFORCE Recommender System](https://mlsanity.com/paper/1812.02353/) (2018)
- [Sequential Recommender Systems: Challenges, Progress and Prospects](https://mlsanity.com/paper/2001.04830/) (2019)
- [Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning](https://mlsanity.com/paper/1802.06501/) (2018)
- [Measuring Recommender System Effects with Simulated Users](https://mlsanity.com/paper/2101.04526/) (2021)
- [Towards Neural Mixture Recommender for Long Range Dependent User Sequences](https://mlsanity.com/paper/1902.08588/) (2019)
- [SiReN: Sign-Aware Recommendation Using Graph Neural Networks](https://mlsanity.com/paper/2108.08735/) (2021)
- [Loss Aversion in Recommender Systems: Utilizing Negative User Preference to Improve Recommendation Quality](https://mlsanity.com/paper/1812.11422/) (2018)
- [Reward Shaping for User Satisfaction in a REINFORCE Recommender](https://mlsanity.com/paper/2209.15166/) (2022)
- [Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Recommendations Tasks](https://mlsanity.com/paper/1607.04228/) (2016)
- [Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning](https://mlsanity.com/paper/2207.13909/) (2022)

## Built on by (most cited first, 7 of 7)

- [Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies](https://mlsanity.com/paper/2409.17436/) (2024)
- [Towards Unified Modeling for Positive and Negative Preferences in Sign-Aware Recommendation](https://mlsanity.com/paper/2403.08246/) (2024)
- [Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback](https://mlsanity.com/paper/2605.29141/) (2026)
- [Negative Feedback for Music Personalization](https://mlsanity.com/paper/2406.04488/) (2024)
- [Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders](https://mlsanity.com/paper/2510.08930/) (2025)
- [CoNRec: Context-Discerning Negative Recommendation with LLMs](https://mlsanity.com/paper/2601.15721/) (2026)
- [Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation](https://mlsanity.com/paper/2608.15877/) (2026)

## Abstract (arXiv)

Sequential recommenders have been widely used in industry due to their strength in modeling user preferences. While these models excel at learning a user's positive interests, less attention has been paid to learning from negative user feedback. Negative user feedback is an important lever of user control, and comes with an expectation that recommenders should respond quickly and reduce similar recommendations to the user. However, negative feedback signals are often ignored in the training objective of sequential retrieval models, which primarily aim at predicting positive user interactions. In this work, we incorporate explicit and implicit negative user feedback into the training objective of sequential recommenders in the retrieval stage using a "not-to-recommend" loss function that optimizes for the log-likelihood of not recommending items with negative feedback. We demonstrate the effectiveness of this approach using live experiments on a large-scale industrial recommender system. Furthermore, we address a challenge in measuring recommender responsiveness to negative feedback by developing a counterfactual simulation framework to compare recommender responses between different user actions, showing improved responsiveness from the modeling change.