相关论文: Generative Active Testing: Efficient LLM Evaluatio…

Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional adaptation approaches, such as fine-tuning, modify the…

Adapting language models to the clinical domain through continued pretraining and instruction tuning requires costly retraining for each new model generation. We propose Cross-Architecture Proxy Tuning (CAPT), a model-ensembling approach…

We study the problem of semi-supervised question answering----utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework, the Generative Domain-Adaptive Nets. In this framework, we…

Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Recent advances in automated test generation utilises language models to produce unit tests. While effective, language models tend to generate many incorrect tests with respect to both syntax and semantics. Although such incorrect tests can…

In supervised learning, acquiring labeled training data for a predictive model can be very costly, but acquiring a large amount of unlabeled data is often quite easy. Active learning is a method of obtaining predictive models with high…

The growing complexity and diversity of news coverage have made framing analysis a crucial yet challenging task in computational social science. Traditional approaches, including manual annotation and fine-tuned models, remain limited by…

Model-Agnostic Meta-Learning (MAML) is a famous few-shot learning method that has inspired many follow-up efforts, such as ANIL and BOIL. However, as an inductive method, MAML is unable to fully utilize the information of query set,…

Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a novel agent capability that can construct cues (or…

The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…

Active learning (AL) has demonstrated remarkable potential in reducing the annotation effort required for training machine learning models. However, despite the surging popularity of natural language generation (NLG) tasks in recent years,…

While most generative models show achievements in image data generation, few are developed for tabular data generation. Recently, due to success of large language models (LLM) in diverse tasks, they have also been used for tabular data…

Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by…

In the context of text classification, the financial burden of annotation exercises for creating training data is a critical issue. Active learning techniques, particularly those rooted in uncertainty sampling, offer a cost-effective…

Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked…

Existing Computerized Adaptive Testing (CAT) frameworks typically select questions based on the predicted likelihood that the student will answer correctly. This design ignores information contained in students' open-ended responses,…

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely…

Evaluating text generation capabilities of large language models (LLMs) is challenging, particularly for low-resource languages where methods for direct assessment are scarce. We propose MUG-Eval, a novel framework that evaluates LLMs'…

The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive running costs, companies or organisations tend to transfer the…