Preprint

Auditing Semantic Gains in Sequential Recommendation: A Lightweight Recovery Test

Kong Wang Zhongke He Xiang Chen Hongwei Zeng Kai Deng Longshaokan Wang Ke Yang

Aug 2026 · 0 citations · 21 references

Computer Science

TL;DR

The results suggest that lightweight recovery from offline item representations and transparent fusion should be ruled out before improvements are attributed to serving-time language modeling, semantic-ID generation, or heavier semantic machinery.

Abstract

Recent semantic and generative-retrieval recommenders report substantial improvements over ID-only sequential baselines, but it remains unclear whether these gains arise from language-model reasoning, semantic-ID generation, end-to-end semantic architectures, stronger offline item representations, or complementary semantic and collaborative signals. We investigate this attribution ambiguity through LIME-Rec, a lightweight and auditable recovery test. LIME-Rec combines three independent experts: a SASRec sequential expert, an ItemCF co-occurrence expert, and a semantic expert based on frozen BAAI/bge-base-en-v1.5 item embeddings. Their full-catalog scores are normalized per user and combined through auditable score-level fusion followed by bounded history calibration. The fusion gate and calibration head are fitted on validation data only, require no serving-time language-model inference, and keep each expert contribution separately inspectable. On Amazon Beauty, Toys, and Sports, LIME-Rec achieves R@10 scores of 0.0996, 0.1105, and 0.0593, outperforming the strongest comparison baseline by 7.0%-12.0%. Three-expert fusion without history calibration consistently outperforms calibrated SASRec, showing that calibration alone does not explain the recovery. Randomly permuting item-text embeddings across item IDs reduces R@10 by 13.6%-17.5%, indicating that the gains depend on genuine item-text correspondence rather than additional representation capacity. These results suggest that lightweight recovery from offline item representations and transparent fusion should be ruled out before improvements are attributed to serving-time language modeling, semantic-ID generation, or heavier semantic machinery.

arXiv Semantic Scholar

View source

Similar papers

Preprint Aug 2026

The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness

It is found 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.

Gustavo Penha, Juan Elenter, Claudia Hauff et al. · 0 citations

#artificial intelligence Preprint Aug 2026

rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation

Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a user's preferences or explaining why one item fits better than another - rather than mapping history directly to a ranked list. This reasoning, however, is expensive to repeat on every ranking request and, once produced, is typically consumed once and discarded, leaving it neither reusable across future requests nor easy to inspect or correct as user tastes drift. Our insight is that reasoning does not need to be regenerated at every call if it can instead be compressed once into a compact, structured memory that a lightweight model retrieves from. We propose rEDMRec, which distills a teacher LLM's reasoning into four typed, editable experience channels - long-term preference, short-term context, item-perception, and counterfactual hard-negative comparisons - maintained by an LLM memory controller that performs Add/Delete/Modify/Keep operations and refines entries via K-agent debate. A lightweight student LLM then ranks candidates purely by retrieving from this memory, without invoking the teacher again, decoupling online inference cost from reasoning depth. Across ML-1M, Amazon Beauty, and Steam and ten student backbones, rEDMRec improves HR@1 over zero-shot, few-shot, and RAG on every backbone, and over GraphRAG on most backbones, with Impv up to 13.3% vs. the second-best baseline on ML-1M. Channel ablations show that short-term context is the only channel that helps consistently across capacity tiers, whereas long-term, item-perception, and counterfactual contributions are capacity-dependent (and can reverse on the strongest students); debate-based memory optimization lowers bank duplication by 7.4 percentage points while raising downstream HR@1 by up to +0.029 over six optimization epochs.

M. H. Nguyen, Tung Le, Huy-Tien Nguyen · 0 citations

Preprint Aug 2026

Difficulty-Aware Semantic-ID Optimization for Generative Recommendation

Difficulty-Aware Semantic-ID Optimization (DASO), a tree-aware post-training method that addresses failure mode as an online rollout-allocation problem and improves over MiniOneRec-style GRPO on 11 of 12 metrics and achieves the best result on 9 of 12 metrics.

Xin Yu, Stephen Li, S. Aghaei et al. · 0 citations

Preprint Aug 2026

DREAM Technical Report

This work presents DREAM (Developing Recommender Engine with Agentic Methods), an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them, supporting agentic meta-control as a viable paradigm for industrial recommendation.

Bin Zhang, Bo-Wen Zheng, Chao Yi et al. · 0 citations

Preprint Aug 2026

Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation

This work proposes a simple, parameter-free intervention that initializes SID token embeddings directly from their corresponding centroids in the semantic embedding space, and shows that preserving SID geometry, beyond shared-prefix structure, provides a simple and effective semantic prior for LLM-based GR.

Donald Loveland, Liam Collins, B. Kumar et al. · 0 citations

Jul 2026

LLM-Based Generative Retrieval for Snapchat Content Recommendation

The design and launch of SnapLGR, an LLM-based generative retrieval system for short-video recommendation at Snapchat shows that successful production SnapLGR requires joint design across representation learning, vocabulary grounding, and efficient training and serving.

Liam Collins, Jiwen Ren, Donald Loveland et al. · arXiv.org · 0 citations