paper-with-me

Papers

When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval

2026-06-11 · Tongyao Zhu, Chao-Ming Huang, Min-Yen Kan arxiv

While mixed-language querying is ubiquitous in multilingual communities, the sensitivity of dense retrievers to such queries remains poorly understood. We present a ratio-controlled study on mMARCO that systematically evaluates retrieval performance by varying the mixing proportion of parallel query translations via embedding-level mixing -- constructing mixed queries as an interpolation of monolingual embeddings. Experiments with BGE-M3 demonstrate that an optimal mixing ratio outperforms the best monolingual endpoint in 88/105 cases. We uncover a distinct asymmetry driven by English dominance: mixing is uniformly beneficial when retrieving from non-English document indices, whereas indices containing English are best served by pure English queries. Furthermore, English acts as the strongest mixing partner for every non-English document language. Finally, when controlling for English dominance, mixing gains correlate negatively with typological distance. We conclude that language-mix sensitivity is structured and predictable, and we validate the robustness of these patterns across model families and scales.

📄 PDF Abstract BibTeX arXiv:2606.13537

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents

2026-06-19 · Mellow Baixuan Chen, Xiangguo Sun arxiv

Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget, and existing memory methods either truncate aggressively and lose non-local evidence or …

When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation

2026-06-18 · Elroy Galbraith arxiv

Streaming Retrieval-Augmented Generation (Streaming RAG) hides tool latency by issuing retrieval queries in parallel with the user's still-arriving input, before the utterance is complete. Speculation can only help, thou…

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

2021-03-09 · CVPR 2021 1 · Masato Tamura, Hiroki Ohashi, Tomoaki Yoshinaga

We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection. HOIs are so diverse in spatial distribution in an image that existing CNN-based methods face the following three major draw…

Human-Object Interaction Concept DiscoveryHuman-Object Interaction Detection

Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction

2022-06-28 · ACL 2022 5 · Keiji Shinzato, Naoki Yoshinaga, Yandi Xia, Wei-Te Chen

A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products. Although this challenge is partially addressed by a question answering (QA) ap…

AttributeAttribute ExtractionAttribute Value ExtractionQuestion Answering

GenLabel: Mixup Relabeling using Generative Models

2022-01-07 · Jy-yong Sohn, Liang Shang, Hongxu Chen, Jaekyun Moon 외

Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades the performance. In this paper, we first…

Adversarial RobustnessData Augmentation