A sequential behavioral alignment framework pairing fine-tuning with preference optimization over paired correct and counterfactual rationales is developed and applied, demonstrating that behavioral alignment mitigates bidirectional rationalization while delivering human-interpretable reasoning traces without manual pipeline overhead.
Abstract
Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale. While Large Language Models (LLMs) offer a promising alternative by predicting user engagement directly from raw text logs, empirical analysis in this study identifies a critical failure mode termed bidirectional rationalization. In a zero-shot setting, LLMs are found to convincingly argue for both positive and negative user engagement outcomes on the exact same item with identical evidence, highlighting the unreliability of off-the-shelf LLMs in predicting user engagement. To resolve this, we develop and apply a sequential behavioral alignment framework pairing fine-tuning with preference optimization over paired correct and counterfactual rationales. Evaluated on real-world homepage interaction logs, this aligned reasoning approach achieves a 32.19\% lift in Macro-F1 score over the zero-shot baseline and matches the production feature-engineered baseline. The results demonstrate that behavioral alignment mitigates bidirectional rationalization while delivering human-interpretable reasoning traces without manual pipeline overhead.
This work introduces PromptPack, a scalable, high-throughput LLM annotation agent that cuts LLM costs by 89% and accelerates throughput by 2.5x while fully preserving AUC.
Sebastian Koralewski, Merwan Barlier, Yulia Stolin et al.· 0 citations
Message search and retrieval on enterprise collaboration platforms is challenging in ''eye-off'' environments, where explicit human relevance labels cannot be collected and engagement signals such as clicks and dwell times are noisy and behaviorally biased. Large Language Models (LLMs) offer an alternative source of semantic supervision, but models trained solely on LLM-derived labels often regress on engagement-based metrics. We present LLM-Click Agreement Labeling, an industrial-scale supervision strategy that retains only those query--message pairs where click-based labels and LLM-generated labels agree. This selective filtering reduces supervision noise and maintains a balance between user interaction patterns and semantic relevance. In a human-annotated pilot, agreement-based labels improved accuracy by +18% relative to click-only supervision. A worldwide A/B deployment further showed that the approach preserves traditional search quality while delivering statistically significant gains in conversational grounding (e.g., +1.4% CiteDCG, +5.7% Good Citation Count). These results highlight that improving supervision quality, rather than modifying model architecture, is the most effective lever for advancing retrieval performance in large-scale enterprise systems.
Avinash Kumar, Hardi Rathod, Rohan Mallick et al.· Annual International ACM SIG...· 0 citations
Recent work has focused on improving explicit natural-language descriptive reasoning traces for generative recommendation. This includes systems that augment semantic ID (SID) prediction with chain-of-thought reasoning. However, because SIDs are opaque learned identifiers rather than natural language, they require costly alignment before an LLM can reason over them. This provides a controlled experimental setting in which both item representation (Title vs. SID) and semantic grounding (minimal vs. extensive SID alignment) can be varied independently. We therefore present the first controlled comparison of descriptive reasoning trace quality across semantic IDs and natural-language titles in a 2 x 2 factorial study on three Amazon product domains using a shared Qwen3-1.7B backbone. We find that introducing explicit descriptive reasoning traces reduces traditional offline recommendation effectiveness under standard SFT and RL training, even though natural language titles produce substantially more grounded and interpretable traces. Extensive SID alignment improves descriptive trace quality but not traditional offline recommendation effectiveness, while a richer reward signal partially recovers performance. Overall, our results show that improving descriptive reasoning trace quality is not, by itself, sufficient to consistently improve traditional offline recommendation effectiveness under the training objectives and evaluation protocols studied here.
Gustavo Penha, Juan Elenter, Claudia Hauff et al.· 0 citations
Conversational Recommendation Systems (CRS) aim to achieve two primary objectives: recommending relevant items and generating natural language responses. While recommendation accuracy is effectively measured by established ranking metrics, the evaluation of response generation poses a more fundamental challenge. Although human evaluation remains the gold standard, its cost and scalability constraints have motivated the adoption of LLM-as-a-judge as a promising proxy, whose alignment with human judgment in the context of CRS remains an open question. In this paper, we present the first user study to empirically assess the reliability of LLM-as-a-judge for evaluating CRS responses. We sample 20 multi-turn music recommendation sessions and generate candidate system responses using four instruction-tuned LLMs, inducing variance in response quality across model scales. We collect $n{=}400$ ratings from 20 domain-expert annotators, who evaluate each response across two dimensions: Personalization Quality and Explanation Quality. Through bootstrapped correlation analysis, we find that LLM-based judges exhibit moderate positive alignment with human assessments and outperform all reference-based baselines. Furthermore, we analyze how judge performance varies according to model scale and conditioning information, providing practical guidance for deploying LLM-as-a-judge.
Seungheon Doh, Bruno Sguerra, Sergio Oramas et al.· 0 citations
Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile. This makes recommendation vulnerable to feedback loops: repeated exposure is mistaken for preference, immediate clicks dominate delayed satisfaction, and fluent explanations need not reflect the ranking decision. We propose our method, a model-agnostic framework for long-horizon recommendation. Our method uses a frozen multimodal language model to convert item content and feedback into evidence-grounded semantic atoms, then maintains separate short-term, long-term, and exposure memories. Propensity-weighted updates reduce policy-induced exposure bias, while a conservative offline critic reranks candidates for delayed satisfaction under a behavior-support constraint. Explanations use only influential evidence atoms and are checked by counterfactual deletion. We provide an identification result and evaluate the framework in e-commerce-like, news-like, and short-video-like environments. Across ten seeds, our method improves discounted long-term value over the strongest alternative by 6.1%, 7.6%, and 6.7%, respectively. Twenty-seed paired ablations show significant value drops after removing propensity correction (0.739 +/- 0.191) or conservative support regularization (0.523 +/- 0.234). A frozen instruction language model also more than doubles semantic-atom NDCG over TF-IDF on a held-out paraphrase benchmark.
Traditional sequential recommender systems have primarily relied on implicit pattern recognition in user interaction sequences, achieving strong performance but functioning as “black boxes” that lack transparent reasoning. This paper introduces LLM-RS, a novel framework that leverages Large Language Models to enable explicit reasoning chains in sequential recommendation. Our approach transforms the recommendation task from mere pattern matching to interpretable reasoning by developing a multi-stage architecture that: (1) extracts structured preference profiles from user interaction sequences, (2) generates explicit reasoning chains analyzing candidate items against inferred preferences, and (3) produces persuasive explanations alongside recommendations. We propose three model variants—fine-tuned reasoning, retrieval-augmented generation, and hybrid ensemble—that integrate LLM-based reasoning with traditional collaborative filtering. The framework addresses key challenges in modern recommender systems by providing transparent, persuasive rationales while maintaining competitive performance, marking a significant step toward more interpretable and trustworthy recommendation systems. Comprehensive evaluations across the Amazon Reviews, MovieLens, MIND, and KuaiSAR datasets demonstrate that LLM-RS not only matches state-of-the-art methods in accuracy but also significantly enhances explanation quality, user trust, and recommendation diversity. Our findings reveal that reasoning-enabled recommendations increase user adherence in online experiments and improve long-term engagement metrics.
A. Gadallah, H. Hefny, Mohammed E. Almandouh et al.· Mathematics· 0 citations