42 citations · 108 across the 20 of their papers we have counts for
21 papers
Symmetric two-level preconditioning for the method of reflections
Jongho Park
We develop and analyze a symmetric two-level preconditioner for the method of reflections for Laplace problems in perforated domains. Using constant boundary modes, we define a coa…
From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale
Cen Mia Zhao, Peng Wang, Chuan Shi +6
Conversational assistants can blend retrieval, action selection, escalation, and wording in a single model path, or separate those roles. We report a production migration of a cust…
LLM-Friendly Knowledge Representation for Customer Support
Hanchen Su, Wei Luo, Wei Han +5
We propose a practical approach by integrating Large Language Models (LLMs) with a framework designed to navigate the complexities of Airbnb customer support operations. In this pa…
Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback
Yisha Wu, Cen Mia Zhao, Yuanpei Cao +4
We introduce an incremental summarization system for customer support agents that intelligently determines when to generate concise bullet notes during conversations, reducing agen…
Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support
Cen Mia Zhao, Tiantian Zhang, Hanchen Su +8
We introduce an Agent-in-the-Loop (AITL) framework that implements a continuous data flywheel for iteratively improving an LLM-based customer support system. Unlike standard offlin…
Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
Sungho Jeon, Ching-Feng Yeh, Hakan Inan +4
In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transfor…
Effective Long-Context Scaling of Foundation Models
Wenhan Xiong, Jingyu Liu, Igor Molybog +18
We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with l…
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oguz, Changsheng Zhao +6
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break d…
VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation
Xilun Chen, Lili Yu, Wenhan Xiong +3
We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is fi…
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
Sheng-Chieh Lin, Akari Asai, Minghan Li +5
Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however…
STRUDEL: Structured Dialogue Summarization for Dialogue Comprehension
Borui Wang, Chengcheng Feng, Arjun Nair +6
Abstractive dialogue summarization has long been viewed as an important standalone task in natural language processing, but no previous work has explored the possibility of whether…
Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences
Asish Ghoshal, Arash Einolghozati, Ankit Arun +6
Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries. In thi…
CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
Minghan Li, Sheng-Chieh Lin, Barlas Oguz +5
Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. T…
Bridging the Training-Inference Gap for Dense Phrase Retrieval
Gyuwan Kim, Jinhyuk Lee, Barlas Oguz +4
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these proced…
Adapting Pretrained Text-to-Text Models for Long Text Sequences
Wenhan Xiong, Anchit Gupta, Shubham Toshniwal +2
We present an empirical study of adapting an existing pretrained text-to-text model for long-sequence inputs. Through a comprehensive study along three axes of the pretraining pipe…
BiT: Robustly Binarized Multi-distilled Transformer
Zechun Liu, Barlas Oguz, Aasish Pappu +5
Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them increasi…
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning
Xiangru Tang, Arjun Nair, Borui Wang +7
Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by u…
Simple Local Attentions Remain Competitive for Long-Context Tasks
Wenhan Xiong, Barlas Oğuz, Anchit Gupta +5
Many NLP tasks require processing long contexts beyond the length limit of pretrained models. In order to scale these models to longer text sequences, many efficient long-range att…
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Xilun Chen, Kushal Lakhotia, Barlas Oğuz +6
Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare…
Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries
Xiangru Tang, Alexander Fabbri, Haoran Li +6
Current pre-trained models applied to summarization are prone to factual inconsistencies which either misrepresent the source text or introduce extraneous information. Thus, compar…
Domain-matched Pre-training Tasks for Dense Retrieval
Barlas Oğuz, Kushal Lakhotia, Anchit Gupta +8
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks. A notable exception is information ret…