Publications (17)
Evaluating the Utility of Grounding Documents with Reference-Free LLM-based Metrics
Yilun Hua, Giuseppe Castellucci, Peter Schulam +2
Retrieval Augmented Generation (RAG)'s success depends on the utility the LLM derives from the content used for grounding. Quantifying content utility does not have a definitive sp…
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
Li Zhou, Kevin Small
Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conve…
WINELL: Wikipedia Never-Ending Updating with LLM Agents
Revanth Gangi Reddy, Tanay Dixit, Jiaxin Qin +7
Wikipedia, a vast and continuously consulted knowledge base, faces significant challenges in maintaining up-to-date content due to its reliance on manual human editors. Inspired by…
SumREN: Summarizing Reported Speech about Events in News
Revanth Gangi Reddy, Heba Elfardy, Hou Pong Chan +2
A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i.e., the 5 Ws; Who,…
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning
Li Zhou, Kevin Small, Yong Zhang +1
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, su…
End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient
Li Zhou, Kevin Small, Oleg Rokhlenko +1
Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies acc…
Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi +1
Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. Ho…
Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement
Chenkai Sun, Ke Yang, Revanth Gangi Reddy +5
The increasing demand for personalized interactions with large language models (LLMs) calls for methodologies capable of accurately and efficiently identifying user opinions and pr…
NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge
Revanth Gangi Reddy, Sai Chetan, Zhenhailong Wang +8
Claim detection and verification are crucial for news understanding and have emerged as promising technologies for mitigating misinformation and disinformation in the news. However…
Summary-Oriented Question Generation for Informational Queries
Xusen Yin, Li Zhou, Kevin Small +1
Users frequently ask simple factoid questions for question answering (QA) systems, attenuating the impact of myriad recent works that support more complex questions. Prompting user…
Background Summarization of Event Timelines
Adithya Pratapa, Kevin Small, Markus Dreyer
Generating concise summaries of news events is a challenging natural language processing task. While journalists often curate timelines to highlight key sub-events, newcomers to a…
Answer Consolidation: Formulation and Benchmarking
Wenxuan Zhou, Qiang Ning, Heba Elfardy +2
Current question answering (QA) systems primarily consider the single-answer scenario, where each question is assumed to be paired with one correct answer. However, in many real-wo…
PLAtE: A Large-scale Dataset for List Page Web Extraction
Aidan San, Yuan Zhuang, Jan Bakus +6
Recently, neural models have been leveraged to significantly improve the performance of information extraction from semi-structured websites. However, a barrier for continued progr…
Fluent Response Generation for Conversational Question Answering
Ashutosh Baheti, Alan Ritter, Kevin Small
Question answering (QA) is an important aspect of open-domain conversational agents, garnering specific research focus in the conversational QA (ConvQA) subtask. One notable limita…
Inverse Reinforcement Learning with Natural Language Goals
Li Zhou, Kevin Small
Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines…
Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
Zixuan Zhang, Revanth Gangi Reddy, Kevin Small +2
Open-domain Question Answering (OpenQA) aims at answering factual questions with an external large-scale knowledge corpus. However, real-world knowledge is not static; it updates a…
Active Learning in Recommendation Systems with Multi-level User Preferences
Yuheng Bu, Kevin Small
While recommendation systems generally observe user behavior passively, there has been an increased interest in directly querying users to learn their specific preferences. In such…