arXiv AI
Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 5
Probe the Harness: Setup Checks for Stale-Data RL Comparisons in Language Models
The paper introduces PTH (Probe The Harness), a set of checks designed to expose hidden details in experimental setups that can alter the ranking of stale-data reinforcement learning methods for language models. By applying PTH to a comparison between SAN and truncated importance sampling (TIS), the authors demonstrate that subtle harness configurations—such as how PPO ratios are computed, data seeding, replay queue reuse, and loss normalisation—can reverse the observed performance order. The study provides a detailed signature of each influencing factor, reference results for TIS and uncorrected GRPO, and a checklist to ensure fair comparisons.
arXiv AI
1d ago
An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation
arXiv:2605.24155v2 Announce Type: replace-cross Abstract: Effective skills-aware talent recommendation must balance behavioral transition patterns, trajectory-sensitive adaptation, and inspectable oc...
arXiv AI
Sep 1
TAAL: Mitigating Early Beam Pruning in Generative Recommendation via Temporal Autoregressive Alignment
arXiv:2608.29179v1 Announce Type: cross Abstract: Generative recommendation encodes items as hierarchical semantic identifiers (SIDs) and retrieves the next item through autoregressive decoding. Stan...
arXiv AI
Aug 24
UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists
UpgradeBench is a decision‑centric longitudinal benchmark that evaluates how fine‑tuned language‑model specialists should be handled when new base‑model releases occur. It covers four consecutive Qwen releases, a continuation checkpoint, six tasks, two model sizes, and OLMo checkpoints with known training lineage, and examines whether retraining, adapter transfer, or other recovery strategies improve specialist performance. The benchmark reveals that upgrade gains vary by task and release interval, that direct adapter copying is sensitive to pretraining distance, and that teacher relabeling can recover specialists without new annotations. "whyItMatters":"The study provides actionable insights into the cost‑effective management of specialist models across model releases, showing how to balance retraining effort with performance gains."
arXiv AI
Aug 7
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
arXiv:2604. 02183v3 Announce Type: replace Abstract: Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned.
arXiv Machine Learning
Aug 26
RetrievalFormer: A Dual-Encoder Transformer for Efficient Approximate Nearest Neighbor Retrieval and Cold-Item Recommendation
arXiv:2608.24079v1 Announce Type: cross Abstract: A shared search-and-recommendation index must score new items from features alone because search has no exploration slot. In a public log covering bo...