相关论文: AdvSumm: Adversarial Training for Bias Mitigation …

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

The automatic evaluation of natural language generation (NLG) systems presents a long-lasting challenge. Recent studies have highlighted various neural metrics that align well with human evaluations. Yet, the robustness of these evaluators…

Extensive efforts in the past have been directed toward the development of summarization datasets. However, a predominant number of these resources have been (semi)-automatically generated, typically through web data crawling, resulting in…

Recent studies have found that summaries generated by large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. Therefore, we study an LLM-as-reference…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks. Specifically, during fine-tuning we generate adversarial examples by perturbing the word embeddings of the…

In malware behavioral analysis, the list of accessed and created files very often indicates whether the examined file is malicious or benign. However, malware authors are trying to avoid detection by generating random filenames and/or…

Adversarial training is a technique of improving model performance by involving adversarial examples in the training process. In this paper, we investigate adversarial training with multiple adversarial examples to benefit the relation…

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference time to generate summaries directly; however, such approaches often suffer from inconsistent LLM outputs…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

The The use of Large language models (LLMs) to summarise parliamentary proceedings presents a promising means of increasing the accessibility of democratic participation. However, as these systems increasingly mediate access to political…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially…

Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard datasets. While these PLMs excel in automatic evaluations, they frequently underperform in human evaluations, indicating a deviation between…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Natural Language Processing (NLP) has recently achieved success by using huge pre-trained Transformer networks. However, these models often contain hundreds of millions or even billions of parameters, bringing challenges to online…

Recently, large language models (LLMs) have demonstrated impressive capabilities in dealing with new tasks with the help of in-context learning (ICL). In the study of Large Vision-Language Models (LVLMs), when implementing ICL, researchers…