# A Reproducibility Analysis of PO4ISR: Diagnosing and Mitigating Semantic Drift in LLM-Based Session Recommendation

arXiv: https://arxiv.org/abs/2605.18780 · HTML: https://mlsanity.com/paper/2605.18780/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 21 of 21)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Neural Attentive Session-based Recommendation](https://mlsanity.com/paper/1711.04725/) (2017)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [A Simple Convolutional Generative Network for Next Item Recommendation](https://mlsanity.com/paper/1808.05163/) (2018)
- [Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction](https://mlsanity.com/paper/2305.06474/) (2023)
- [Multi-Interest Network with Dynamic Routing for Recommendation at Tmall](https://mlsanity.com/paper/1904.08030/) (2019)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [Intent Contrastive Learning for Sequential Recommendation](https://mlsanity.com/paper/2202.02519/) (2022)
- [Improved Recurrent Neural Networks for Session-based Recommendations](https://mlsanity.com/paper/1606.08117/) (2016)
- [Global Context Enhanced Graph Neural Networks for Session-based Recommendation](https://mlsanity.com/paper/2106.05081/) (2021)
- [Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1911.11942/) (2019)
- [TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation](https://mlsanity.com/paper/2005.02844/) (2020)
- [Large Language Models for Intent-Driven Session Recommendations](https://mlsanity.com/paper/2312.07552/) (2023)
- [Modeling Multi-aspect Preferences and Intents for Multi-behavioral Sequential Recommendation](https://mlsanity.com/paper/2309.14938/) (2023)

## Abstract (arXiv)

Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of their reasoning capabilities across diverse semantic domains remains unexplored. In this work, we conduct a rigorous reproducibility study of PO4ISR to assess its generalization limits. Our analysis reveals a critical failure mode: standard reasoning prompts suffer from severe contextual drift in long sessions, leading to performance degradation on semantically complex datasets like Games and Bundle. To quantify and resolve this stability gap, we introduce PO4ISR++, a robustness-enhanced implementation that integrates reflexive prompting and consistent rank detection. Unlike the original static prompting strategy, our approach dynamically adapts to cross-domain cues. We benchmark both the original implementation and our robust variant on ML-1M, Games, and Bundle. Our results confirm that while the original model struggles in new domains, our reproducible extension restores performance, yielding a stabilized gain of up to 54% on Games and 96% on Bundle. We release open-source artifacts, including the reproduced baseline and our enhanced framework, to facilitate reliable future research in LLM-based recommendation.