Search
39 resources
-
Weizhe Yuan, Graham Neubig, Pengfei Liu,...|Dec 27th, 2021|journalArticleWeizhe Yuan, Graham Neubig, Pengfei Liu,...Dec 27th, 2021
A wide variety of NLP applications, such as machine translation, summarization, and dialog, involve text generation. One major challenge for these applications is how to evaluate whether such generated texts are actually fluent, accurate, or effective. In this work, we conceptualize the evaluation of generated text as a text generation problem, modeled using pre-trained sequence-to-sequence models. The general idea is that models trained to convert the generated text to/from a reference...
-
Liu|Aug 27th, 2024|conferencePaperLiuAug 27th, 2024
-
Ming Zhong, Yang Liu, Da Yin|Oct 13th, 2022|preprintMing Zhong, Yang Liu, Da YinOct 13th, 2022
Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency. However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models. In this paper, we propose a unified multi-dimensional evaluator UniEval for NLG. We re-frame NLG...
-
Shashank Sonkar, Naiming Liu, Debshila M...|Dec 27th, 2023|conferencePaperShashank Sonkar, Naiming Liu, Debshila M...Dec 27th, 2023
-
Jinlan Fu, See-Kiong Ng, Zhengbao Jiang,...|Dec 27th, 2023|journalArticleJinlan Fu, See-Kiong Ng, Zhengbao Jiang,...Dec 27th, 2023
Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models. Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently. This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities...
-
Annenberg Institute at Brown...|Jun 3rd, 2023|reportAnnenberg Institute at Brown...Jun 3rd, 2023
Providing consistent, individualized feedback to teachers is essential for improving instruction but can be prohibitively resource-intensive in most educational contexts. We develop M-Powering Teachers, an automated tool based on natural language processing to give teachers feedback on their uptake of student contributions, a high-leverage dialogic teaching practice that makes students feel heard. We conduct a randomized controlled trial in an online computer science course (n=1,136...
-
Gyeong-Geon Lee, Ehsan Latif, Xuansheng ...|Dec 27th, 2023|journalArticleGyeong-Geon Lee, Ehsan Latif, Xuansheng ...Dec 27th, 2023
This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the challenges of accessibility, technical complexity, and lack of explainability that have previously limited the use of artificial intelligence-based automatic scoring tools among researchers and educators. With a testing dataset comprising six assessment...
-
Yiqing Xie, Alex Xie, Divyanshu Sheth|Mar 31st, 2024|preprintYiqing Xie, Alex Xie, Divyanshu ShethMar 31st, 2024
To facilitate evaluation of code generation systems across diverse scenarios, we present CodeBenchGen, a framework to create scalable execution-based benchmarks that only requires light guidance from humans. Specifically, we leverage a large language model (LLM) to convert an arbitrary piece of code into an evaluation example, including test cases for execution-based evaluation. We illustrate the usefulness of our framework by creating a dataset, Exec-CSN, which includes 1,931 examples...
-
Yiqing Xie, Alex Xie, Divyanshu Sheth|Mar 31st, 2024|preprintYiqing Xie, Alex Xie, Divyanshu ShethMar 31st, 2024
To facilitate evaluation of code generation systems across diverse scenarios, we present CodeBenchGen, a framework to create scalable execution-based benchmarks that only requires light guidance from humans. Specifically, we leverage a large language model (LLM) to convert an arbitrary piece of code into an evaluation example, including test cases for execution-based evaluation. We illustrate the usefulness of our framework by creating a dataset, Exec-CSN, which includes 1,931 examples...
-
Yang Liu, Dan Iter, Yichong Xu|May 23rd, 2023|preprintYang Liu, Dan Iter, Yichong XuMay 23rd, 2023
The quality of texts generated by natural language generation (NLG) systems is hard to measure automatically. Conventional reference-based metrics, such as BLEU and ROUGE, have been shown to have relatively low correlation with human judgments, especially for tasks that require creativity and diversity. Recent studies suggest using large language models (LLMs) as reference-free metrics for NLG evaluation, which have the benefit of being applicable to new tasks that lack human references....
-
Chi-Min Chan, Weize Chen, Yusheng Su|Aug 14th, 2023|preprintChi-Min Chan, Weize Chen, Yusheng SuAug 14th, 2023
Text evaluation has historically posed significant challenges, often demanding substantial labor and time cost. With the emergence of large language models (LLMs), researchers have explored LLMs' potential as alternatives for human evaluation. While these single-agent-based approaches show promise, experimental results suggest that further advancements are needed to bridge the gap between their current effectiveness and human-level evaluation quality. Recognizing that best practices of human...
-
Lei Huang, Weijiang Yu, Weitao Ma|Nov 9th, 2023|preprintLei Huang, Weijiang Yu, Weitao MaNov 9th, 2023
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), leading to remarkable advancements in text understanding and generation. Nevertheless, alongside these strides, LLMs exhibit a critical tendency to produce hallucinations, resulting in content that is inconsistent with real-world facts or user inputs. This phenomenon poses substantial challenges to their practical deployment and raises concerns over the reliability of...
-
Steven Moore, John Stamper, Richard Tong...|Jul 7th, 2023|conferencePaperSteven Moore, John Stamper, Richard Tong...Jul 7th, 2023
-
Steven Moore, John Stamper, Richard Tong...|Jul 7th, 2023|conferencePaperSteven Moore, John Stamper, Richard Tong...Jul 7th, 2023
-
Matyáš Boháček, Steven Moore, John Stamp...|Jul 7th, 2023|conferencePaperMatyáš Boháček, Steven Moore, John Stamp...Jul 7th, 2023
-
Andrew M. Olney, Steven Moore, John Stam...|Jul 7th, 2023|conferencePaperAndrew M. Olney, Steven Moore, John Stam...Jul 7th, 2023
-
Matyáš Boháček, Steven Moore, John Stamp...|Jul 7th, 2023|conferencePaperMatyáš Boháček, Steven Moore, John Stamp...Jul 7th, 2023
-
Md Rayhan Kabir, Fuhua Lin, Steven Moore...|Jul 7th, 2023|conferencePaperMd Rayhan Kabir, Fuhua Lin, Steven Moore...Jul 7th, 2023
-
Shashank Sonkar, Richard G. Baraniuk, St...|Jul 7th, 2023|conferencePaperShashank Sonkar, Richard G. Baraniuk, St...Jul 7th, 2023
-
Qianou Christina Ma, Sherry Tongshuang W...|Jul 7th, 2023|conferencePaperQianou Christina Ma, Sherry Tongshuang W...Jul 7th, 2023