More Like this

1. Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning

   Lu, P.; Qiu, L.; Chang, K. W.; Wu, Y. N.; Zhu, S. C.; Rajpurohit, T.; Clark, K.; Kalyan, A. (May 2023, International Conference on Learning Representations (ICLR 2023))

   Mathematical reasoning, a core ability of human intelligence, presents unique challenges for machines in abstract thinking and logical reasoning. Recent large pre-trained language models such as GPT-3 have achieved remarkable progress on mathematical reasoning tasks written in text form, such as math word problems (MWP). However, it is unknown if the models can handle more complex problems that involve math reasoning over heterogeneous information, such as tabular data. To fill the gap, we present Tabular Math Word Problems (TABMWP), a new dataset containing 38,431 open-domain grade-level problems that require mathematical reasoning on both textual and tabular data. Each question in TABMWP is aligned with a tabular context, which is presented as an image, semi-structured text, and a structured table. There are two types of questions: free-text and multi-choice, and each problem is annotated with gold solutions to reveal the multi-step reasoning process. We evaluate different pre-trained models on TABMWP, including the GPT-3 model in a few-shot setting. As earlier studies suggest, since few-shot GPT-3 relies on the selection of in-context examples, its performance is unstable and can degrade to near chance. The unstable issue is more severe when handling complex problems like TABMWP. To mitigate this, we further propose a novel approach, PROMPTPG, which utilizes policy gradient to learn to select in-context examples from a small amount of training data and then constructs the corresponding prompt for the test example. Experimental results show that our method outperforms the best baseline by 5.31% on the accuracy metric and reduces the prediction variance significantly compared to random selection, which verifies its effectiveness in selecting in-context examples. 

   more » « less
2. Training LLMs to Recognize Hedges in Dialogues about Roadrunner Cartoons

   https://doi.org/10.18653/v1/2024.sigdial-1.18  

   Paige, Amie; Soubki, Adil; Murzaku, John; Rambow, Owen; Brennan, Susan E (January 2024, Association for Computational Linguistics)

   Hedges allow speakers to mark utterances as provisional, whether to signal non-prototypicality or “fuzziness”, to indicate a lack of commitment to an utterance, to attribute responsibility for a statement to someone else, to invite input from a partner, or to soften critical feedback in the service of face management needs. Here we focus on hedges in an experimentally parameterized corpus of 63 Roadrunner cartoon narratives spontaneously produced from memory by 21 speakers for co-present addressees, transcribed to text (Galati and Brennan, 2010). We created a gold standard of hedges annotated by human coders (the Roadrunner-Hedge corpus) and compared three LLM-based approaches for hedge detection: fine-tuning BERT, and zero and few-shot prompting with GPT-4o and LLaMA-3. The best-performing approach was a fine-tuned BERT model, followed by few-shot GPT-4o. After an error analysis on the top performing approaches, we used an LLM-in-the-Loop approach to improve the gold standard coding, as well as to highlight cases in which hedges are ambiguous in linguistically interesting ways that will guide future research. This is the first step in our research program to train LLMs to interpret and generate collateral signals appropriately and meaningfully in conversation. 

   more » « less
3. What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks

   Guo, T; Guo, K; Nan, B; Liang, Z; Guo, Z; Chawla, NV; Wiest, O; Zhang, X (December 2023, 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. GazeGraph: graph-based few-shot cognitive context sensing from human visual behavior

   https://doi.org/10.1145/3384419.3430774  

   Lan, Guohao; Heit, Bailey; Scargill, Tim; Gorlatova, Maria (November 2020, Proceedings of the 18th Conference on Embedded Networked Sensor Systems)

   null (Ed.)

   In this work, we present GazeGraph, a system that leverages human gazes as the sensing modality for cognitive context sensing. GazeGraph is a generalized framework that is compatible with different eye trackers and supports various gaze-based sensing applications. It ensures high sensing performance in the presence of heterogeneity of human visual behavior, and enables quick system adaptation to unseen sensing scenarios with few-shot instances. To achieve these capabilities, we introduce the spatial-temporal gaze graphs and the deep learning-based representation learning method to extract powerful and generalized features from the eye movements for context sensing. Furthermore, we develop a few-shot gaze graph learning module that adapts the `learning to learn' concept from meta-learning to enable quick system adaptation in a data-efficient manner. Our evaluation demonstrates that GazeGraph outperforms the existing solutions in recognition accuracy by 45% on average over three datasets. Moreover, in few-shot learning scenarios, GazeGraph outperforms the transfer learning-based approach by 19% to 30%, while reducing the system adaptation time by 80%. 

   more » « less
5. Leveraging Large Language Models for Evaluating Explanations in Math Education. Learning Analytics and Knowledge

   Worden, E; Croteau, E; Cheng, L; McReynolds, A; Heffernan, N (January 2024, LAK 2024 (submitted, in review))

   Human-conducted rating tasks are resource-intensive and demand significant time and financial commitments. As Large Language Models (LLMs) like GPT emerge and exhibit prowess across various domains, their potential in automating such evaluation tasks becomes evident. In this research, we leveraged four prominent LLMs: GPT-4, GPT-3.5, Vicuna, and PaLM 2, to scrutinize their aptitude in evaluating teacher-authored mathematical explanations. We utilized a detailed rubric that encompassed accuracy, explanation clarity, the correctness of mathematical notation, and the efficacy of problem-solving strategies. During our investigation, we unexpectedly discerned the influence of HTML formatting on these evaluations. Notably, GPT-4 consistently favored explanations formatted with HTML, whereas the other models displayed mixed inclinations. When gauging Inter-Rater Reliability (IRR) among these models, only Vicuna and PaLM 2 demonstrated high IRR using the conventional Cohen’s Kappa metric for explanations formatted with HTML. Intriguingly, when a more relaxed version of the metric was applied, all model pairings showcased robust agreement. These revelations not only underscore the potential of LLMs in providing feedback on student-generated content but also illuminate new avenues, such as reinforcement learning, which can harness the consistent feedback from these models. 

   more » « less