Related papers: Benchmarking and Improving Generator-Validator Con…

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: \textit{predicting when an LLM grader is likely to be…

Machine-Generated Text (MGT) is becoming increasingly difficult to distinguish from Human-Written Text (HWT). This trend has exacerbated malicious activities such as fake news and online fraud. The generalization ability of fine-tuned…

Large language models (LLMs) have become mainstream technology with their versatile use cases and impressive performance. Despite the countless out-of-the-box applications, LLMs are still not reliable. A lot of work is being done to improve…

Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing…

Incorporating specific knowledge into large language models via retrieval-augmented generation (RAG) is a widespread technique that fuels many of today's industry AI applications. A fundamental problem is to assess if the context retrieved…

ChatGPT has demonstrated impressive performance in various downstream tasks. However, in the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to…

Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with…

Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to provide appropriate answers in many cases. In this paper, we…

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack…

Small language models like T5 excel in generating high-quality text for data-to-text tasks, offering adaptability and cost-efficiency compared to Large Language Models (LLMs). However, they frequently miss keywords, which is considered one…

Large language models (LLMs) are prone to hallucinations and sensitive to prompt perturbations, often resulting in inconsistent or unreliable generated text. Different methods have been proposed to mitigate such hallucinations and…

Background: Manual testing is vital for detecting issues missed by automated tests, but specifying accurate verifications is challenging. Aims: This study aims to explore the use of Large Language Models (LLMs) to produce verifications for…

Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is…

Dominant accuracy evaluation might reward unwarranted guessing of Large Language Models, and it might not be applicable to novel tasks for model validation without ground-truth (gt) annotation. Based on basic logic principle, we propose a…

Large language models (LLMs) are increasingly being used for tasks where outputs shape human decisions, so it is critical to verify that their responses consistently reflect desired human values. Humans, as individuals or groups, don't…

GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 on several…

Qualitative analysis is typically limited to small datasets because it is time-intensive. Moreover, a second human rater is required to ensure reliable findings. Artificial intelligence tools may replace human raters if we demonstrate high…

Despite significant progress in Visual Question Answering over the years, robustness of today's VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that…

Augmented generation techniques such as Retrieval-Augmented Generation (RAG) and Cache-Augmented Generation (CAG) have revolutionized the field by enhancing large language model (LLM) outputs with external knowledge and cached information.…

Context: ChatGPT and other large language models (LLMs) are widely used across healthcare, business, economics, engineering, and software engineering (SE). Despite their popularity, concerns persist about their reliability, especially their…