Proposes UMBRELA, an open-source toolkit using GPT-4 for automatic relevance assessment, showing high correlation with human judgments.

Shivani Upadhyay, Ronak Pradeep, Nandan Thakur et al.

Proposes multivariate policy learning for multi-objective recommendation, maximizing a conservative lower bound on the North Star reward in continuous action spaces.

Olivier Jeunen, Jatin Mandav, Ivan Potapov et al.

Proposed CoST uses contrastive quantization to improve semantic tokens, boosting Recall@5 by 43%.

Jieming Zhu, Mengqun Jin, Qijiong Liu et al.

Join-aware multi-table retrieval using mixed-integer programming improves F1 by 9.3%.

Peter Baile Chen, Yi Zhang, Dan Roth

Semantic search engine for mathlib4 using large language models and vector similarity, achieving 50%+ improvement over baselines.

Guoxiong Gao, Haocheng Ju, Jiedong Jiang et al.

This study compares data augmentation and contrastive learning in sequential recommendation, finding certain augmentation strategies can match or outperform contrastive methods.

Peilin Zhou, You-Liang Huang, Yueqi Xie et al.

SPLADE-v3 achieves over 40 MR R@10 on MS MARCO, improves out-of-domain results by 2%, surpassing BM25 and SPLADE++ via training innovations.

Carlos Lassance, Hervé Déjean, Thibault Formal et al.

ToolRerank combines adaptive truncation and hierarchy-aware reranking, significantly improving tool retrieval accuracy.

Yuanhang Zheng, Peng Li, Wei Liu et al.

Proposes CoRAL, a reinforcement learning-based retrieval strategy to incorporate collaborative info, enhancing long-tail recommendation with LLMs.

Junda Wu, Cheng-Chun Chang, Tong Yu et al.

Proposes Uplift-guided Budget Allocation (UBA) for target user attacks, estimating heterogeneous treatment effects via path number proxies to optimize fake user budgets.

Wenjie Wang, Changsheng Wang, Fuli Feng et al.

Proposes Lower-Left Partial AUC (LLPAUC) as an efficient, top-K aligned metric for recommendation, validated through theory and experiments, improving ranking performance.

Wentao Shi, Chenxu Wang, Fuli Feng et al.

Proposes TedRec, a Fourier transform-based sequence-level semantic fusion method that improves recommendation accuracy by 14%-38% across five datasets.

Lanling Xu, Zhen Tian, Bingqian Li et al.

Using Transformer models for symbolic music generation and retrieval, enhancing MIR efficiency.

Dinh-Viet-Toan Le, Louis Bigo, Mikaela Keller et al.

MACRec uses multi-agent collaboration to reframe recommendation for 4 tasks.

Zhefan Wang, Yuanqing Yu, Wendi Zheng et al.

Proposes Sliver sliding window data stream paradigm, boosting live recommendation timeliness and accuracy, with a 6.76% CTR increase demonstrated.

Fengqi Liang, Baigong Zheng, Liqin Zhao et al.

Proposed NESCL model improves collaborative filtering via neighborhood-enhanced supervised contrastive learning, achieving 10.09% NDCG@20 improvement on Yelp2018.

Peijie Sun, Le Wu, Kun Zhang et al.

This paper proposes Lite-LLM4Rec, a hierarchical LLM architecture that eliminates beam search, reducing inference time by 97.28% and boosting performance by 46.8%.

Hanbing Wang, Xiaorui Liu, Wenqi Fan et al.

This study systematically analyzes retrieval strategies in RAG, showing random documents can boost accuracy by up to 35%.

Florin Cuconasu, Giovanni Trappolini, Federico Siciliano et al.

Introduced persona-centric metamorphic relations for robustness testing; prompt learning shows lower violation rates (~20%) compared to other paradigms.

Yanbing Chen, Lin Li, Xiaohui Tao et al.

Leveraging large language models (LLMs) for graph augmentation significantly improves recommendation accuracy under data sparsity.

Wei Wei, Xubin Ren, Jiabin Tang et al.