skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Prompting as Panacea? A Case Study of In-Context Learning Performance for Qualitative Coding of Classroom Dialog
One of the areas where Large Language Models (LLMs) show promise is for automated qualitative coding, typically framed as a text classification task in natural language processing (NLP). Their demonstrated ability to leverage in-context learning to operate well even in data-scarce settings poses the question of whether collecting and annotating large-scale data for training qualitative coding models is still beneficial. In this paper, we empirically investigate the performance of LLMs designed for use in prompting-based in-context learning settings, and draw a comparison to models that have been trained using the traditional pretraining--finetuning paradigm with task-specific annotated data, specifically for tasks involving qualitative coding of classroom dialog. Compared to other domains where NLP studies are typically situated, classroom dialog is much more natural and therefore messier. Moreover, tasks in this domain are nuanced and theoretically grounded and require a deep understanding of the conversational context. We provide a comprehensive evaluation across five datasets, including tasks such as talkmove prediction and collaborative problem solving skill identification. Our findings show that task-specific finetuning strongly outperforms in-context learning, showing the continuing need for high-quality annotated training datasets.  more » « less
Award ID(s):
2326170
PAR ID:
10536555
Author(s) / Creator(s):
; ; ; ; ;
Editor(s):
Benjamin, Paaßen; Carrie, Demmans Epp
Publisher / Repository:
International Educational Data Mining Society
Date Published:
Format(s):
Medium: X
Right(s):
Creative Commons Attribution 4.0 International
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Association for Computational Linguistics)
    Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use. 
    more » « less
  2. ; ; ; ; ; ; ; ; (, ACM Computing Surveys)
    Dialog systems (e.g., chatbots) have been widely studied, yet related research that leverages artificial intelligence (AI) and natural language processing (NLP) is constantly evolving. These systems have typically been developed to interact with humans in the form of speech, visual, or text conversation. As humans continue to adopt dialog systems for various objectives, there is a need to involve humans in every facet of the dialog development life cycle for synergistic augmentation of both the humans and the dialog system actors in real-world settings. We provide a holistic literature survey on the recent advancements inhuman-centered dialog systems(HCDS). Specifically, we provide background context surrounding the recent advancements in machine learning-based dialog systems and human-centered AI. We then bridge the gap between the two AI sub-fields and organize the research works on HCDS under three major categories (i.e., Human-Chatbot Collaboration, Human-Chatbot Alignment, Human-Centered Chatbot Design & Governance). In addition, we discuss the applicability and accessibility of the HCDS implementations through benchmark datasets, application scenarios, and downstream NLP tasks. 
    more » « less
  3. ; ; ; ; ; ; ; (, 37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks.)
    Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering. However, the capability of LLMs to advance the field of chemistry remains unclear. In this paper, rather than pursuing state-of-the-art performance, we aim to evaluate capabilities of LLMs in a wide range of tasks across the chemistry domain. We identify three key chemistryrelated capabilities including understanding, reasoning and explaining to explore in LLMs and establish a benchmark containing eight chemistry tasks. Our analysis draws on widely recognized datasets facilitating a broad exploration of the capacities of LLMs within the context of practical chemistry. Five LLMs (GPT-4, GPT-3.5, Davinci-003, Llama and Galactica) are evaluated for each chemistry task in zero-shot and few-shot in-context learning settings with carefully selected demonstration examples and specially crafted prompts. Our investigation found that GPT-4 outperformed other models and LLMs exhibit different competitive levels in eight chemistry tasks. In addition to the key findings from the comprehensive benchmark analysis, our work provides insights into the limitation of current LLMs and the impact of in-context learning settings on LLMs’ performance across various chemistry tasks. The code and datasets used in this study are available at https://github.com/ChemFoundationModels/ChemLLMBench. 
    more » « less
  4. ; (, Advances in neural information processing systems)
    Does prompting a large language model (LLM) like GPT-3 with explanations improve in-context learning? We study this question on two NLP tasks that involve reasoning over text, namely question answering and natural language inference. We test the performance of four LLMs on three textual reasoning datasets using prompts that include explanations in multiple different styles. For these tasks, we find that including explanations in the prompts for OPT, GPT-3 (davinci), and InstructGPT (text-davinci-001) only yields small to moderate accuracy improvements over standard few-show learning. However, text-davinci-002 is able to benefit more substantially. We further show that explanations generated by the LLMs may not entail the models' predictions nor be factually grounded in the input, even on simple tasks with extractive explanations. However, these flawed explanations can still be useful as a way to verify LLMs' predictions post-hoc. Through analysis in our three settings, we show that explanations judged by humans to be good---logically consistent with the input and the prediction---more likely cooccur with accurate predictions. Following these observations, we train calibrators using automatically extracted scores that assess the reliability of explanations, allowing us to improve performance post-hoc across all of our datasets. 
    more » « less
  5. ; ; ; (, Findings of the Association for Computational Linguistics: EMNLP 2023)
    Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks (e.g., knowledge acquisition tasks). In this paper, we seek to assess and enhance LLMs’ contextual faithfulness in two aspects: knowledge conflict and prediction with abstention. We demonstrate that LLMs’ faithfulness can be significantly improved using carefully designed prompting strategies. In particular, we identify opinion-based prompts and counterfactual demonstrations as the most effective methods. Opinion-based prompts reframe the context as a narrator’s statement and inquire about the narrator’s opinions, while counterfactual demonstrations use instances containing false facts to improve faithfulness in knowledge conflict situations. Neither technique requires additional training. We conduct experiments on three datasets of two standard NLP tasks, machine reading comprehension and relation extraction, and the results demonstrate significant improvement in faithfulness to contexts. Code and data are released at https://github.com/wzhouad/context-faithful-llm. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email