Search Results - "Galley, Michel"

Understanding Emotions in Text Using Deep Learning and Big Data by Chatterjee, Ankush, Gupta, Umang, Chinnakotla, Manoj Kumar, Srikanth, Radhakrishnan, Galley, Michel, Agrawal, Puneet

“…Big Data and Deep Learning algorithms combined with enormous computing power have paved ways for significant technological advancements. Technology is evolving…”
Get full text

Overview of the seventh Dialog System Technology Challenge: DSTC7 by D’Haro, Luis Fernando, Yoshino, Koichiro, Hori, Chiori, Marks, Tim K., Polymenakos, Lazaros, Kummerfeld, Jonathan K., Galley, Michel, Gao, Xiang

“…•DSTC7: Dialog Challenge to build more robust and accurate end-to-end dialog systems.•Track 1, Sentence selection for multiple domains, including variations…”
Get full text

Overview of the Eighth Dialog System Technology Challenge: DSTC8 by Kim, Seokhwan, Galley, Michel, Gunasekara, Chulaka, Lee, Sungjin, Atkinson, Adam, Peng, Baolin, Schulz, Hannes, Gao, Jianfeng, Li, Jinchao, Adada, Mahmoud, Huang, Minlie, Lastras, Luis, Kummerfeld, Jonathan K., Lasecki, Walter S., Hori, Chiori, Cherian, Anoop, Marks, Tim K., Rastogi, Abhinav, Zang, Xiaoxue, Sunkara, Srinivas, Gupta, Raghav

“…This paper introduces the Eighth Dialog System Technology Challenge. In line with recent challenges, the eighth edition focuses on applying end-to-end dialog…”
Get full text

Measuring machine translation quality as semantic equivalence: A metric based on entailment features by Padó, Sebastian, Cer, Daniel, Galley, Michel, Jurafsky, Dan, Manning, Christopher D.

“…Current evaluation metrics for machine translation have increasing difficulty in distinguishing good from merely fair translations. We believe the main problem…”
Get full text

AutoCaption: Automatic caption generation for personal photos by Ramnath, Krishnan, Baker, Simon, Vanderwende, Lucy, El-Saban, Motaz, Sinha, Sudipta N., Kannan, Anitha, Hassan, Noran, Galley, Michel, Yi Yang, Ramanan, Deva, Bergamo, Alessandro, Torresani, Lorenzo

“…AutoCaption is a system that helps a smartphone user generate a caption for their photos. It operates by uploading the photo to a cloud service where a number…”
Get full text

Teaching Language Models to Self-Improve through Interactive Demonstrations by Yu, Xiao, Peng, Baolin, Galley, Michel, Gao, Jianfeng, Yu, Zhou

“…The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant…”
Get full text

Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models by Li, Miaoran, Peng, Baolin, Galley, Michel, Gao, Jianfeng, Zhang, Zhu

“…Fact-checking is an essential task in NLP that is commonly utilized for validating the factual accuracy of claims. Prior work has mainly focused on fine-tuning…”
Get full text

Instruction Tuning with GPT-4 by Peng, Baolin, Li, Chunyuan, He, Pengcheng, Galley, Michel, Gao, Jianfeng

“…Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable…”
Get full text

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning by Yu, Xiao, Peng, Baolin, Vajipey, Vineeth, Cheng, Hao, Galley, Michel, Gao, Jianfeng, Yu, Zhou

“…Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language…”
Get full text

Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog by Li, Miaoran, Peng, Baolin, Galley, Michel, Gao, Jianfeng, Zhang, Zhu

“…Many efforts have been made to construct dialog systems for different types of conversations, such as task-oriented dialog (TOD) and open-domain dialog (ODD)…”
Get full text

Rethinking Interpretability in the Era of Large Language Models by Singh, Chandan, Inala, Jeevana Priya, Galley, Michel, Caruana, Rich, Gao, Jianfeng

“…Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural…”
Get full text

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities by Sun, Chung-En, Liu, Xiaodong, Yang, Weiwei, Weng, Tsui-Wei, Cheng, Hao, San, Aidan, Galley, Michel, Gao, Jianfeng

“…Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms…”
Get full text

Probing Factually Grounded Content Transfer with Factual Ablation by West, Peter, Quirk, Chris, Galley, Michel, Choi, Yejin

“…Despite recent success, large neural models often generate factually incorrect text. Compounding this is the lack of a standard automatic evaluation for…”
Get full text

MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform by Gao, Xiang, Galley, Michel, Dolan, Bill

“…We present MixingBoard, a platform for quickly building demos with a focus on knowledge grounded stylized text generation. We unify existing text generation…”
Get full text

Self-Verification Improves Few-Shot Clinical Information Extraction by Gero, Zelalem, Singh, Chandan, Cheng, Hao, Naumann, Tristan, Galley, Michel, Gao, Jianfeng, Poon, Hoifung

“…IMLH 2023 Extracting patient information from unstructured text is a critical task in health decision-support and clinical research. Large language models…”
Get full text

Interactive Text Generation by Faltings, Felix, Galley, Michel, Peng, Baolin, Brantley, Kianté, Cai, Weixin, Zhang, Yizhe, Gao, Jianfeng, Dolan, Bill

“…Users interact with text, image, code, or other editors on a daily basis. However, machine learning models are rarely trained in the settings that reflect the…”
Get full text

Automatic Document Sketching: Generating Drafts from Analogous Texts by Wu, Zeqiu, Galley, Michel, Brockett, Chris, Zhang, Yizhe, Dolan, Bill

“…The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document…”
Get full text

Guiding Large Language Models via Directional Stimulus Prompting by Li, Zekun, Peng, Baolin, He, Pengcheng, Galley, Michel, Gao, Jianfeng, Yan, Xifeng

“…We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of…”
Get full text

An Adversarially-Learned Turing Test for Dialog Generation Models by Gao, Xiang, Zhang, Yizhe, Galley, Michel, Dolan, Bill

“…The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing…”
Get full text

Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge by Majumder, Bodhisattwa Prasad, Rao, Sudha, Galley, Michel, McAuley, Julian

“…The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing…”
Get full text