RETSim: Resilient and Efficient Text Similarity
This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks. We demonstrate that RETSim is significantly more robust and accurate than MinHash and neural text embeddings, achieving new state-of-the-art performance on dataset deduplication, adversarial text retrieval benchmarks, and spam clustering tasks. We also introduce the W4NT3D benchmark (Wiki-40B 4dversarial Near-T3xt Dataset) for evaluating multilingual, near-duplicate text retrieval capabilities under adversarial settings. RETSim and the W4NT3D benchmark are open-sourced under the MIT License at https://github.com/google/unisim.
Code (3)
Tasks
Adversarial TextClusteringRetrievalText Retrievaltext similaritySimilar Papers 제목 키워드 기반
Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold…
Text-to-Image GenerationGraph Neural NetworkReLATE: Resilient Learner Selection for Multivariate Time-Series Classification Against Adversarial Attacks
Minimizing computational overhead in time-series classification, particularly in deep learning models, presents a significant challenge. This challenge is further compounded by adversarial attacks, emphasizing the need f…
Adversarial AttackDeep LearningModel SelectionTime Series+1Byzantine Resilient Distributed Multi-Task Learning
Distributed multi-task learning provides significant advantages in multi-agent networks with heterogeneous data sources where agents aim to learn distinct but correlated models simultaneously.However, distributed algorit…
Multi-Task LearningReasoning to Attend: Try to Understand How <SEG> Token Works
Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on $\texttt{<SEG>}$ token as a text prompt to jointly optimize the vision-language model (e.g., LLaVA) and the downstream task-specified mo…
Semantic SimilaritySemantic Textual SimilarityVisual GroundingResilience for Distributed Consensus with Constraints
This paper proposes a new approach that enables multi-agent systems to achieve resilient \textit{constrained} consensus in the presence of Byzantine attacks, in contrast to existing literature that is only applicable to …