Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation

• URL: http://arxiv.org/abs/2604.03724v1
• Date: Sat, 04 Apr 2026 13:01:45 GMT
• Title: Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation
• Abstract summary: We formalize explainable recommendation as a statement-level ranking problem.<n>This formulation mitigates hallucination by construction and enables fine-grained factual analysis.<n>We introduce StaR, a benchmark for statement ranking in explainable recommendation, constructed from four Amazon Reviews 2014 product categories.
• Score: 2.3534886273639457
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Textual explanations, generated with large language models (LLMs), are increasingly used to justify recommendations. Yet, evaluating these explanations remains a critical challenge. We advocate a shift in objective: rank, don't generate. We formalize explainable recommendation as a statement-level ranking problem, where systems rank candidate explanatory statements derived from reviews and return the top-k as explanation. This formulation mitigates hallucination by construction and enables fine-grained factual analysis. It also models factor importance through relevance scores and supports standardized, reproducible evaluation with established ranking metrics. Meaningful assessment, however, requires each statement to be explanatory (item facts affecting user experience), atomic (one opinion about one aspect), and unique (paraphrases consolidated), which is challenging to obtain from noisy reviews. We address this with (i) an LLM-based extraction pipeline producing explanatory and atomic statements, and (ii) a scalable, semantic clustering method consolidating paraphrases to enforce uniqueness. Building on this pipeline, we introduce StaR, a benchmark for statement ranking in explainable recommendation, constructed from four Amazon Reviews 2014 product categories. We evaluate popularity-based baselines and state-of-the-art models under global-level (all statements) and item-level (target item statements) ranking. Popularity baselines are competitive in global-level ranking but outperform state-of-the-art models on average in item-level ranking, exposing critical limitations in personalized explanation ranking.

Related papers

• Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation [60.55792673956761]
  We propose textbfRubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation.<n>We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance.
  arXiv  Detail & Related papers  (2026-06-17T17:54:04Z)
• Prompt Perturbation for Reliable LLM Evaluation over Comparison Graphs [10.095945693317079]
  evaluating large language models (LLMs) is important for understanding their capabilities, comparing competing systems, and supporting the deployment of reliable models in practice.<n>For open-ended tasks, pairwise evaluation has become a popular paradigm, in which two responses to the same prompt are compared and the resulting judgments are aggregated into an overall ranking.<n>A central challenge of this paradigm is intransitivity: the induced comparison outcomes may fail to support any coherent global ranking.
  arXiv  Detail & Related papers  (2026-06-16T07:44:45Z)
• On the Factual Consistency of Text-based Explainable Recommendation Models [2.2153783542347805]
  We introduce a comprehensive framework for evaluating the factual consistency of text-based explainable recommenders.<n>We design a prompting-based pipeline that uses LLMs to extract atomic explanatory statements from reviews.<n>We propose statement-level alignment metrics that combine LLM- and NLI-based approaches to assess both factual consistency and relevance of generated explanations.
  arXiv  Detail & Related papers  (2025-12-30T17:25:15Z)
• RankList -- A Listwise Preference Learning Framework for Predicting Subjective Preferences [66.76322360727809]
  We propose RankList, a listwise preference learning framework that generalizes RankNet to structured list-level supervision.<n>Our formulation explicitly models local and non-local ranking constraints within a probabilistic framework.<n>Extensive experiments demonstrate the superiority of our method across diverse modalities.
  arXiv  Detail & Related papers  (2025-08-13T13:59:41Z)
• In-context Ranking Preference Optimization [65.5489745857577]
  We propose an In-context Ranking Preference Optimization (IRPO) framework to optimize large language models (LLMs) based on ranking lists constructed during inference.<n>We show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.
  arXiv  Detail & Related papers  (2025-04-21T23:06:12Z)
• AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings [53.78802457488845]
  We introduce the idea of any-granularity ranking, which leverages multi-vector embeddings to rank at varying levels of granularity. We demonstrate the application of proposition-level ranking to post-hoc citation addition in retrieval-augmented generation.
  arXiv  Detail & Related papers  (2024-05-23T20:04:54Z)
• RankingSHAP -- Listwise Feature Attribution Explanations for Ranking Models [48.895510739010355]
  We present three key contributions to address this gap.<n>First, we rigorously define listwise feature attribution for ranking models.<n>Second, we introduce RankingSHAP, extending the popular SHAP framework to accommodate listwise ranking attribution.<n>Third, we propose two novel evaluation paradigms for assessing the faithfulness of attributions in learning-to-rank models.
  arXiv  Detail & Related papers  (2024-03-24T10:45:55Z)
• Hierarchical Indexing for Retrieval-Augmented Opinion Summarization [60.5923941324953]
  We propose a method for unsupervised abstractive opinion summarization that combines the attributability and scalability of extractive approaches with the coherence and fluency of Large Language Models (LLMs) Our method, HIRO, learns an index structure that maps sentences to a path through a semantically organized discrete hierarchy. At inference time, we populate the index and use it to identify and retrieve clusters of sentences containing popular opinions from input reviews.
  arXiv  Detail & Related papers  (2024-03-01T10:38:07Z)
• Rank-LIME: Local Model-Agnostic Feature Attribution for Learning to Rank [16.780058676633914]
  Rank-LIME is a model-agnostic, local, post-hoc linear feature attribution method for the task of learning to rank. We employ novel correlation-based perturbations, differentiable ranking loss functions and introduce new metrics to evaluate ranking based additive feature attribution models.
  arXiv  Detail & Related papers  (2022-12-24T12:14:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.