Search Results for author:
Found 8 papers, 4 papers with code
Attribute First, then Generate: Locally-attributable Grounded Text Generation
Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections.
Multi-Review Fusion-in-Context
This study lays the groundwork for further exploration of modular text generation in the multi-document setting, offering potential improvements in the quality and reliability of generated content.
The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models
In this paper, we explore the behavior of LLMs when presented with (un)answerable queries.
Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans
Further, we substantially improve the silver training data quality via GPT-4 distillation.
SummHelper: Collaborative Human-Computer Summarization
Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process.
Controlled Text Reduction
Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it.
Semantics-aware Attention Improves Neural Machine Translation
We further show an additional gain when using both semantic and syntactic structures in some language pairs.
Mediators in Determining what Processing BERT Performs First
Probing neural models for the ability to perform downstream tasks using their activation patterns is often used to localize what parts of the network specialize in performing what tasks.
