- City University of Hong KongHK4 papers
- Peking UniversityCN2 papers
- Centre National de la Recherche ScientifiqueFR1 paper
- China Institute of Finance and Capital MarketsCN1 paper
- Chinese University of Hong KongHK1 paper
- Hong Kong Polytechnic UniversityHK1 paper
- Huazhong University of Science and TechnologyCN1 paper
- Institute of Science Tokyo1 paper
- Michigan State UniversityUS1 paper
- National University of SingaporeSG1 paper
- North West Agriculture and Forestry University1 paper
- Peking University Shenzhen HospitalCN1 paper
Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
Peiyang Liu, Qiang Yan, Ziqiang Cui +3
Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-maki…
cs.CL2026
Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
Ailiang Lin, Zhuoyun Li, Yusong Wang +2
Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limitations of causal attention in re…