Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees

Kumar, Yaman; Krishna, Sriram; Shah, Rajiv Ratn; Chen, Changyou

doi:10.1609/aaai.v36i11.21563

Cited by 4 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Often, scientific reasoning subscores are heavily weighted towards the negative class (i.e., a large majority of the students do not demonstrate scientific reasoning). Cohen's QWK was chosen because it is widely used in the automated essay scoring (AES) literature (Singh et al 2023;Singla et al 2022). Unlike traditional Cohen's k (Cohen 1960), Cohen's QWK accounts for the degree of disagreement, making it well-suited for ordinal data.…”

Section: Resultsmentioning

confidence: 99%

“…Advances in natural language processing (NLP) have produced improved automated assessment scoring approaches to support teaching and learning (e.g., Adair et al 2023;Wilson et al 2021). Proposed methodologies include data augmentation , next sentence prediction (Wu et al 2023), prototypical neural networks (Zeng et al 2023), cross-prompt fine-tuning (Funayama et al 2023), human-in-the-loop scoring via sam-pling responses (Singla et al 2022), and reinforcement learning (Liu et al 2022). While these methods have enjoyed varying degrees of success, a majority of these applications have targeted more structured mathematics and computer science tasks (i.e., tasks that can be solved formulaically), but their grading is different from scoring free-form shortanswer responses by middle school students in science domains.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students’ Formative Assessment Responses in Science

Cohn,

Hutchins,

et al. 2024

AAAI

View full text Add to dashboard Cite

This paper explores the use of large language models (LLMs) to score and explain short-answer assessments in K-12 science. While existing methods can score more structured math and computer science assessments, they often do not provide explanations for the scores. Our study focuses on employing GPT-4 for automated assessment in middle school Earth Science, combining few-shot and active learning with chain-of-thought reasoning. Using a human-in-the-loop approach, we successfully score and provide meaningful explanations for formative assessment responses. A systematic analysis of our method's pros and cons sheds light on the potential for human-in-the-loop techniques to enhance automated grading for open-ended science assessments.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students’ Formative Assessment Responses in Science

Cohn,

Hutchins,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Similarly, it has been a common complaint that AES systems focus unjustifiably on obscure and difficult vocabulary (Perelman et al, 2014a). While earlier, each score generated by the AI systems was verified by an expert human rater, it is concerning to see that now many of them are scoring independently without any intervention by human experts (O'Donnell, 2020;Singla et al, 2022a). The concerns are further alleviated by the fact that the scores awarded by such systems are used in life-changing decisions ranging from college and job applications to visa approvals (ETS, 2020b;Educational Testing Association, 2019;USBE, 2020;Institute, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…These models, apart from defending AES systems against samples causing oversensitivity and overstability, can also inform effective human intervention strategy. For instance, AES deployments either completely rely on double scoring essay samples (human and machine) or solely on machine ratings alone (ETS, 2020a;Singla et al, 2022a). With the developed model, AES deployments can choose to have an effective middle ground by selecting samples for human testing and intervention more effectively.…”

Section: Introductionmentioning

confidence: 99%

Automatic Essay Scoring Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses

Kumar

Parekh

Singh

et al. 2023

dad

View full text Add to dashboard Cite

Deep-learning based Automatic Essay Scoring (AES) systems are being actively used in various high-stake applications in education and testing. However, little research has been put to understand and interpret the black-box nature of deep-learning-based scoring algorithms. While previous studies indicate that scoring models can be easily fooled, in this paper, we explore the reason behind their surprising adversarial brittleness. We utilize recent advances in interpretability to find the extent to which features such as coherence, content, vocabulary, and relevance are important for automated scoring mechanisms. We use this to investigate the oversensitivity (i.e., large change in output score with a little change in input essay content) and overstability (i.e., little change in output scores with large changes in input essay content) of AES. Our results indicate that autoscoring models, despite getting trained as “end-to-end” models with rich contextual embeddings such as BERT, behave like bag-of-words models. A few words determine the essay score without the requirement of any context making the model largely overstable. This is in stark contrast to recent probing studies on pre-trained representation learning models, which show that rich linguistic features such as parts-of-speech and morphology are encoded by them. Further, we also find that the models have learnt dataset biases, making them oversensitive. The presence of a few words with high co-occurrence with a certain score class makes the model associate the essay sample with that score. This causes score changes in ∼95% of samples with an addition of only a few words. To deal with these issues, we propose detection-based protection models that can detect oversensitivity and samples causing overstability with high accuracies. We find that our proposed models are able to detect unusual attribution patterns and flag adversarial samples successfully.

show abstract

“…AES utilizes Natural Language Processing (NLP) and Machine Learning (ML) techniques to evaluate these essays in a more efficient and scalable manner. Commonly used in standardized tests like the GRE and the TOEFL (Attali and Burstein 2006), many organizations and education councils have turned to use AES to reduce workload (Singla et al 2022).…”

Section: Introductionmentioning

confidence: 99%

H-AES: Towards Automated Essay Scoring for Hindi

Shubhankar

Anirudh

Mital

et al. 2023

AAAI

View full text Add to dashboard Cite

The use of Natural Language Processing (NLP) for Automated Essay Scoring (AES) has been well explored in the English language, with benchmark models exhibiting performance comparable to human scorers. However, AES in Hindi and other low-resource languages remains unexplored. In this study, we reproduce and compare state-of-the-art methods for AES in the Hindi domain. We employ classical feature-based Machine Learning (ML) and advanced end-to-end models, including LSTM Networks and Fine-Tuned Transformer Architecture, in our approach and derive results comparable to those in the English language domain. Hindi being a low-resource language, lacks a dedicated essay-scoring corpus. We train and evaluate our models using translated English essays and empirically measure their performance on our own small-scale, real-world Hindi corpus. We follow this up with an in-depth analysis discussing prompt-specific behavior of different language models implemented.

show abstract

Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees

Cited by 4 publications

References 26 publications

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students’ Formative Assessment Responses in Science

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students’ Formative Assessment Responses in Science

Automatic Essay Scoring Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses

H-AES: Towards Automated Essay Scoring for Hindi

Contact Info

Product

Resources

About