871 citations · 3k across the 87 of their papers we have counts for
88 papers
Parameter-Efficient Detoxification with Contrastive Decoding
Tong Niu, Caiming Xiong, Semih Yavuz +1
The field of natural language generation has witnessed significant advancements in recent years, including the development of controllable text generation techniques. However, cont…
Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems
Lidiya Murakhovs'ka, Philippe Laban, Tian Xie +2
Making big purchases requires consumers to research or consult a salesperson to gain domain expertise. However, existing conversational recommender systems (CRS) often overlook use…
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
Ansong Ni, Pengcheng Yin, Yilun Zhao +11
Recently, large language models (LLMs), especially those that are pretrained on code, have demonstrated strong capabilities in generating programs from natural language inputs in a…
Beyond the Chat: Executable and Verifiable Text-Editing with LLMs
Philippe Laban, Jesse Vig, Marti A. Hearst +2
Conversational interfaces powered by Large Language Models (LLMs) have recently become a popular way to obtain feedback during document editing. However, standard chat-based conver…
XGen-7B Technical Report
Erik Nijkamp, Tian Xie, Hiroaki Hayashi +22
Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LL…
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
Kung-Hsiang Huang, Philippe Laban, Alexander R. Fabbri +4
Previous research in multi-document news summarization has typically concentrated on collating information that all sources agree upon. However, the summarization of diverse inform…
Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System
Jianguo Zhang, Stephen Roller, Kun Qian +6
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capab…
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
Zhiwei Liu, Weiran Yao, Jianguo Zhang +12
The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs). An LAA is able to generate actions with its core…
Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs
Ye Liu, Semih Yavuz, Rui Meng +4
The integration of retrieved passages and large language models (LLMs), such as ChatGPTs, has significantly contributed to improving open-domain question answering. However, there…
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Weiran Yao, Shelby Heinecke, Juan Carlos Niebles +12
Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objecti…
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
Yu Bai, Fan Chen, Huan Wang +2
Neural sequence models based on the transformer architecture have demonstrated remarkable \emph{in-context learning} (ICL) abilities, where they can perform new tasks when prompted…
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Jianguo Zhang, Kun Qian, Zhiwei Liu +7
Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversi…
REX: Rapid Exploration and eXploitation for AI Agents
Rithesh Murthy, Shelby Heinecke, Juan Carlos Niebles +12
In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as…
Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
Fan Yin, Jesse Vig, Philippe Laban +3
Large language models (LLMs) have shown impressive performance in following natural language instructions to solve unseen tasks. However, it remains unclear whether models truly un…
Preference-grounded Token-level Guidance for Language Model Fine-tuning
Shentao Yang, Shujian Zhang, Congying Xia +3
Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence l…
SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages
Philippe Laban, Jesse Vig, Wojciech Kryscinski +3
Text simplification research has mostly focused on sentence-level simplification, even though many desirable edits - such as adding relevant background information or reordering co…
LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond
Philippe Laban, Wojciech Kryściński, Divyansh Agarwal +4
With the recent appearance of LLMs in practical settings, having methods that can effectively detect factual inconsistencies is crucial to reduce the propagation of misinformation…
Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training
Ziwei Fan, Zhiwei Liu, Shelby Heinecke +4
Existing recommender systems face difficulties with zero-shot items, i.e. items that have no historical interactions with users during the training stage. Though recent works extra…
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Can Qin, Shu Zhang, Ning Yu +10
Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffus…
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Le Xue, Ning Yu, Shu Zhang +8
Recent advancements in multimodal pre-training have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts,…
HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution
Ye Liu, Semih Yavuz, Rui Meng +3
The dominant paradigm of textual question answering systems is based on end-to-end neural networks, which excels at answering natural language questions but falls short on complex…
CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong +2
Large language models (LLMs) have demonstrated remarkable abilities in representation learning for program synthesis and understanding tasks. The quality of the learned representat…
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Lifu Tu, Jin Qu, Semih Yavuz +4
Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rat…
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Can Qin, Ning Yu, Chen Xing +6
Text-to-image (T2I) models based on diffusion processes have achieved remarkable success in controllable image generation using user-provided captions. However, the tight coupling…