# RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation

arXiv: https://arxiv.org/abs/2609.00918 · HTML: https://mlsanity.com/paper/2609.00918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Fine-Grained Spoiler Detection from Large-Scale Review Corpora](https://mlsanity.com/paper/1905.13416/) (2019)
- [Evaluating LLMs at Detecting Errors in LLM Responses](https://mlsanity.com/paper/2404.03602/) (2024)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs](https://mlsanity.com/paper/2503.09382/) (2025)
- [How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation](https://mlsanity.com/paper/2503.09598/) (2025)
- [RecGPT: Generative Pre-training for Text-based Recommendation](https://mlsanity.com/paper/2405.12715/) (2024)
- [Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models](https://mlsanity.com/paper/2505.23715/) (2025)
- [Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling](https://mlsanity.com/paper/2506.00064/) (2025)

## Abstract (arXiv)

Large language models are increasingly used as interactive recommender assistants. Their evaluation should therefore go beyond plausible item recommendation and test whether they can recognize flawed recommendation requests. Existing recommender benchmarks mainly assess ranking, generation, or preference satisfaction, while existing error-detection benchmarks are usually not grounded in recommendation-specific user and candidate evidence. To address this gap, we introduce RPCBench, a benchmark for evaluating Recommender-Premise Critique: the ability to detect, diagnose, and properly handle faulty premises in natural-language recommendation requests. RPCBench contains evidence-grounded test instances from five recommendation domains and covers ten types of premise failures. Each instance provides a visible recommendation context and a corrupted user query. We further design a fine-grained evaluation framework that measures proactive detection, error localization, post-detection handling strategy, and evidence faithfulness. Through a systematic evaluation of 11 LLMs, we find that proactive detection is the main bottleneck in Recommender-Premise Critique, and models perform worst on underspecified-premise errors. We also observe that target-critical information density matters more than redundant evidence, and that longer reasoning does not monotonically improve critique quality: performance peaks at intermediate reasoning length, while overly long reasoning is accompanied by an overthinking penalty. The code is available at https://github.com/ZhongruChen/RPCBench.