44 citations · 76 across the 15 of their papers we have counts for
15 papers
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
Weigao Sun, Jiaxi Hu, Yucheng Zhou +12
Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer m…
A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering
Chenliang Zhang, Lin Wang, Yuanyuan Lu +4
This paper describes the solutions of the Dianping-Trust-Safety team for the META CRAG-MM challenge. The challenge requires building a comprehensive retrieval-augmented generation…
RIRAG: Regulatory Information Retrieval and Answer Generation
Tuba Gokhan, Kexin Wang, Iryna Gurevych +1
Regulatory documents, issued by governmental regulatory bodies, establish rules, guidelines, and standards that organizations must adhere to for legal compliance. These documents,…
Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
Yongxin Huang, Kexin Wang, Goran Glavaš +1
Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such…
Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning
Jiaan Wang, Jianfeng Qu, Kexin Wang +4
Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\emph{e.g.}, knowledge graphs; KGs). Recently…
AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification
Yongxin Huang, Kexin Wang, Sourav Dutta +3
Recent work has found that few-shot sentence classification based on pre-trained Sentence Encoders (SEs) is efficient, robust, and effective. In this work, we investigate strategie…
SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval
Nandan Thakur, Kexin Wang, Iryna Gurevych +1
Traditionally, sparse retrieval systems relied on lexical representations to retrieve documents, such as BM25, dominated information retrieval tasks. With the onset of pre-trained…
DAPR: A Benchmark on Document-Aware Passage Retrieval
Kexin Wang, Nils Reimers, Iryna Gurevych
The work of neural retrieval so far focuses on ranking short texts and is challenged with long documents. There are many cases where the users want to find a relevant passage withi…
UKP-SQuARE v3: A Platform for Multi-Agent QA Research
Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva +5
The continuous development of Question Answering (QA) datasets has drawn the research community's attention toward multi-domain models. A popular approach is to use multi-dataset m…
Semantic Similarity Models for Depression Severity Estimation
Anxo Pérez, Neha Warikoo, Kexin Wang +2
Depressive disorders constitute a severe public health issue worldwide. However, public health systems have limited capacity for case detection and diagnosis. In this regard, the w…
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner +6
Question Answering (QA) systems are increasingly deployed in applications where they support real-world decisions. However, state-of-the-art models rely on deep neural networks, wh…
UKP-SQUARE: An Online Platform for Question Answering Research
Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva +10
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require…
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
Kexin Wang, Nandan Thakur, Nils Reimers +1
Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not availab…
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning
Kexin Wang, Nils Reimers, Iryna Gurevych
Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In t…
Understanding Memory Modules on Learning Simple Algorithms
Kexin Wang, Yu Zhou, Shaonan Wang +2
Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms. However, we still have little understanding o…