Search Results for author:
Found 20 papers, 14 papers with code
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
When evaluating 5 LLMs on our benchmarks, we observe that on average, up to 75% of the content in LLM-generated summary is hallucinated, with hallucinations more likely to occur towards the end of the summaries.
Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
While retrieval-augmented generation (RAG) models excel in accessing information from large document collections, they struggle with complex tasks that require aggregation and reasoning over information spanning across multiple documents--what we call holistic reasoning.
A Blueprint Architecture of Compound AI Systems for Enterprise
Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases.
AmbigNLG: Addressing Task Ambiguity in Instruction for NLG
We introduce AmbigNLG, a novel task designed to tackle the challenge of task ambiguity in instructions for Natural Language Generation (NLG).
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models
We demonstrate the efficacy of our finer-grained metric and insights through an adaptive retrieval system that selectively employs retrieval and recall based on the frequencies of entities and relations in the question.
Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related Tasks
We meticulously craft this benchmark to cater to a wide array of HR tasks, including matching and explaining resumes to job descriptions, extracting skills and experiences from resumes, and editing resumes.
XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates
Text editing is a crucial task of modifying text to better align with user intents.
Less is More for Long Document Summary Evaluation by LLMs
Large Language Models (LLMs) have shown promising performance in summary evaluation tasks, yet they face challenges such as high computational costs and the Lost-in-the-Middle problem where important information in the middle of long documents is often overlooked.
Zero-shot Triplet Extraction by Template Infilling
We propose a novel framework, ZETT (ZEro-shot Triplet extraction by Template infilling), that aligns the task objective to the pre-training objective of generative transformers to generalize to unseen relations.
Ranked #1 on
Zero-shot Relation Triplet Extraction
on FewRel
Noisy Pairing and Partial Supervision for Stylized Opinion Summarization
To tackle the difficulty in collecting customer and professional review pairs, we develop a non-parallel training framework, Noisy Pairing and Partial Supervision (NAPA), which trains a stylized opinion summarization system from non-parallel customer and professional review sets.
AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation
Lexically constrained text generation is one of the constrained text generation tasks, which aims to generate text that covers all the given constraint lexicons.
Comparative Opinion Summarization via Collaborative Decoding
Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews.
Biomedical Entity Linking with Contrastive Context Matching
We introduce BioCoM, a contrastive learning framework for biomedical entity linking that uses only two resources: a small-sized dictionary and a large number of raw biomedical articles.
End-to-end Biomedical Entity Linking with Span-based Dictionary Matching
Disease name recognition and normalization, which is generally called biomedical entity linking, is a fundamental process in biomedical text mining.
Convex Aggregation for Opinion Summarization
We found that text autoencoders tend to generate overly generic summaries from simply averaged latent vectors due to an unexpected $L_2$-norm shrinkage in the aggregated latent vectors, which we refer to as summary vector degeneration.
Ranked #1 on
Unsupervised Opinion Summarization
on Amazon
Fact-based Text Editing
We propose a novel text editing task, referred to as \textit{fact-based text editing}, in which the goal is to revise a given document to better describe the facts in a knowledge base (e. g., several triples).
Ranked #1 on
Fact-based Text Editing
on WebEdit
Learning to Select, Track, and Generate for Data-to-Text
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation.
Multivariate Linear Regression of Symptoms-related Tweets for Infectious Gastroenteritis Scale Estimation
Based on these results, we can infer that social sensors can reliably detect unseasonal and local disease events under certain conditions, just as they can for seasonal or global events.
Density Estimation for Geolocation via Convolutional Mixture Density Network
Nowadays, geographic information related to Twitter is crucially important for fine-grained applications.
Forecasting Word Model: Twitter-based Influenza Surveillance and Prediction
Because of the increasing popularity of social media, much information has been shared on the internet, enabling social media users to understand various real world events.
