Liam Dugan


pdf bib
Enhancing Human Summaries for Question-Answer Generation in Education
Hannah Gonzalez | Liam Dugan | Eleni Miltsakaki | Zhiqi Cui | Jiaxuan Ren | Bryan Li | Shriyash Upadhyay | Etan Ginsberg | Chris Callison-Burch
Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)

We address the problem of generating high-quality question-answer pairs for educational materials. Previous work on this problem showed that using summaries as input improves the quality of question generation (QG) over original textbook text and that human-written summaries result in higher quality QG than automatic summaries. In this paper, a) we show that advances in Large Language Models (LLMs) are not yet sufficient to generate quality summaries for QG and b) we introduce a new methodology for enhancing bullet point student notes into fully fledged summaries and find that our methodology yields higher quality QG. We conducted a large-scale human annotation study of generated question-answer pairs for the evaluation of our methodology. In order to aid in future research, we release a new dataset of 9.2K human annotations of generated questions.

pdf bib
Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications
Andrew Zhu | Liam Dugan | Alyssa Hwang | Chris Callison-Burch
Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)

Language model applications are becoming increasingly popular and complex, often including features like tool usage and retrieval augmentation. However, existing frameworks for such applications are often opinionated, deciding for developers how their prompts ought to be formatted and imposing limitations on customizability and reproducibility. To solve this we present Kani: a lightweight, flexible, and model-agnostic open-source framework for building language model applications. Kani helps developers implement a variety of complex features by supporting the core building blocks of chat interaction: model interfacing, chat management, and robust function calling. All Kani core functions are easily overridable and well documented to empower developers to customize functionality for their own needs. Kani thus serves as a useful tool for researchers, hobbyists, and industry professionals alike to accelerate their development while retaining interoperability and fine-grained control.

pdf bib
Exploring the Curious Case of Code Prompts
Li Zhang | Liam Dugan | Hainiu Xu | Chris Callison-burch
Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)

Recent work has shown that prompting language models with code-like representations of natural language leads to performance improvements on structured reasoning tasks. However, such tasks comprise only a small subset of all natural language tasks. In our work, we seek to answer whether or not code-prompting is the preferred way of interacting with language models in general. We compare code and text prompts across three popular GPT models (davinci, code-davinci-002, and text-davinci-002) on a broader selection of tasks (e.g., QA, sentiment, summarization) and find that with few exceptions, code prompts do not consistently outperform text prompts. Furthermore, we show that the style of code prompt has a large effect on performance for some (but not all) tasks and that fine-tuning on text instructions leads to better relative performance of code prompts.


pdf bib
A Feasibility Study of Answer-Agnostic Question Generation for Education
Liam Dugan | Eleni Miltsakaki | Shriyash Upadhyay | Etan Ginsberg | Hannah Gonzalez | DaHyeon Choi | Chuning Yuan | Chris Callison-Burch
Findings of the Association for Computational Linguistics: ACL 2022

We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or un-interpretable questions and that such errors can be ameliorated by providing summarized input. We find that giving these models human-written summaries instead of the original text results in a significant increase in acceptability of generated questions (33% 83%) as determined by expert annotators. We also find that, in the absence of human-written summaries, automatic summarization can serve as a good middle ground.

pdf bib
The Case for a Single Model that can Both Generate Continuations and Fill-in-the-Blank
Daphne Ippolito | Liam Dugan | Emily Reif | Ann Yuan | Andy Coenen | Chris Callison-Burch
Findings of the Association for Computational Linguistics: NAACL 2022

The task of inserting text into a specified position in a passage, known as fill in the blank (FitB), is useful for a variety of applications where writers interact with a natural language generation (NLG) system to craft text. While previous work has tackled this problem with models trained specifically to do fill in the blank, a more useful model is one that can effectively perform _both_ FitB and continuation tasks. In this work, we evaluate the feasibility of using a single model to do both tasks. We show that models pre-trained with a FitB-style objective are capable of both tasks, while models pre-trained for continuation are not. Finally, we show how these models can be easily finetuned to allow for fine-grained control over the length and word choice of the generation.


pdf bib
RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text
Liam Dugan | Daphne Ippolito | Arun Kirubarajan | Chris Callison-Burch
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

In recent years, large neural networks for natural language generation (NLG) have made leaps and bounds in their ability to generate fluent text. However, the tasks of evaluating quality differences between NLG systems and understanding how humans perceive the generated text remain both crucial and difficult. In this system demonstration, we present Real or Fake Text (RoFT), a website that tackles both of these challenges by inviting users to try their hand at detecting machine-generated text in a variety of domains. We introduce a novel evaluation task based on detecting the boundary at which a text passage that starts off human-written transitions to being machine-generated. We show preliminary results of using RoFT to evaluate detection of machine-generated news articles.