Search Results - "Laban, Philippe"

SummaC : Re-Visiting NLI-based Models for Inconsistency Detection in Summarization by Laban, Philippe, Schnabel, Tobias, Bennett, Paul N., Hearst, Marti A.

“…In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous work has found that natural…”
Get full text

Unsupervised Text Generation and Its Application to News Interfaces by Laban, Philippe

“…Recent progress in automated text generation relies predominantly on the use of large datasets, sometimes requiring millions of examples for each application…”
Get full text

Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits by Chakrabarty, Tuhin, Laban, Philippe, Wu, Chien-Sheng

“…LLM-based applications are helping people write, and LLM-generated text is making its way into social media, journalism, and our classrooms. However, the…”
Get full text

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents by Tang, Liyan, Laban, Philippe, Durrett, Greg

“…Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded…”
Get full text

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems by Laban, Philippe, Fabbri, Alexander R, Xiong, Caiming, Wu, Chien-Sheng

“…LLMs and RAG systems are now capable of handling millions of input tokens or more. However, evaluating the output quality of such systems on long-context tasks…”
Get full text

Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment by Laban, Philippe, Murakhovs'ka, Lidiya, Xiong, Caiming, Wu, Chien-Sheng

“…The interactive nature of Large Language Models (LLMs) theoretically allows models to refine and improve their answers, yet systematic analysis of the…”
Get full text

Automatic and Human-AI Interactive Text Generation by Dou, Yao, Laban, Philippe, Gardent, Claire, Xu, Wei

“…In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then…”
Get full text

Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage by Xie, Kaige, Laban, Philippe, Choubey, Prafulla Kumar, Xiong, Caiming, Wu, Chien-Sheng

“…Evaluating retrieval-augmented generation (RAG) systems remains challenging, particularly for open-ended questions that lack definitive answers and require…”
Get full text

Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses by Venkit, Pranav Narayanan, Laban, Philippe, Zhou, Yilun, Mao, Yixin, Wu, Chien-Sheng

“…Large Language Model (LLM)-based applications are graduating from research prototypes to products serving millions of users, influencing how people write and…”
Get full text

What's The Latest? A Question-driven News Chatbot by Laban, Philippe, Canny, John, Hearst, Marti A

“…ACL Demos (2020) 380-387 This work describes an automatic news chatbot that draws content from a diverse set of news articles and creates conversations with a…”
Get full text

News Headline Grouping as a Challenging NLU Task by Laban, Philippe, Bandarkar, Lucas, Hearst, Marti A

“…Recent progress in Natural Language Understanding (NLU) has seen the latest models outperform human performance on many standard tasks. These impressive…”
Get full text

Prompt Leakage effect and defense strategies for multi-turn LLM interactions by Agarwal, Divyansh, Fabbri, Alexander R, Risher, Ben, Laban, Philippe, Joty, Shafiq, Wu, Chien-Sheng

“…Prompt leakage poses a compelling security and privacy threat in LLM applications. Leakage of system prompts may compromise intellectual property, and act as…”
Get full text

Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets by Laban, Philippe, Wu, Chien-Sheng, Liu, Wenhao, Xiong, Caiming

“…Precisely assessing the progress in natural language generation (NLG) tasks is challenging, and human evaluation to establish a preference in a model's output…”
Get full text

CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments by Huang, Kung-Hsiang, Prabhakar, Akshara, Dhawan, Sidharth, Mao, Yixin, Wang, Huan, Savarese, Silvio, Xiong, Caiming, Laban, Philippe, Wu, Chien-Sheng

“…Customer Relationship Management (CRM) systems are vital for modern enterprises, providing a foundation for managing customer interactions and data…”
Get full text

Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems by Murakhovs'ka, Lidiya, Laban, Philippe, Xie, Tian, Xiong, Caiming, Wu, Chien-Sheng

“…Making big purchases requires consumers to research or consult a salesperson to gain domain expertise. However, existing conversational recommender systems…”
Get full text

Beyond the Chat: Executable and Verifiable Text-Editing with LLMs by Laban, Philippe, Vig, Jesse, Hearst, Marti A, Xiong, Caiming, Wu, Chien-Sheng

“…Conversational interfaces powered by Large Language Models (LLMs) have recently become a popular way to obtain feedback during document editing. However,…”
Get full text

Art or Artifice? Large Language Models and the False Promise of Creativity by Chakrabarty, Tuhin, Laban, Philippe, Agarwal, Divyansh, Muresan, Smaranda, Wu, Chien-Sheng

“…Researchers have argued that large language models (LLMs) exhibit high-quality writing capabilities from blogs to stories. However, evaluating objectively the…”
Get full text

SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization by Laban, Philippe, Schnabel, Tobias, Bennett, Paul N, Hearst, Marti A

“…In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous work has found that natural…”
Get full text

Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning by Yin, Fan, Vig, Jesse, Laban, Philippe, Joty, Shafiq, Xiong, Caiming, Wu, Chien-Sheng Jason

“…Large language models (LLMs) have shown impressive performance in following natural language instructions to solve unseen tasks. However, it remains unclear…”
Get full text

SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages by Laban, Philippe, Vig, Jesse, Kryscinski, Wojciech, Joty, Shafiq, Xiong, Caiming, Wu, Chien-Sheng

“…Text simplification research has mostly focused on sentence-level simplification, even though many desirable edits - such as adding relevant background…”
Get full text