Related papers: On the Robustness of Knowledge Editing for Detoxif…

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad adoption. However, the robustness of these LLM-based…

Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation and hallucination detection, motivating a growing interest in efficient probe-based approaches. Yet it remains unclear…

Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Knowledge editing has emerged as an efficient technique for updating the knowledge of large language models (LLMs), attracting increasing attention in recent years. However, there is a lack of effective measures to prevent the malicious…

Large language models for code have achieved strong performance across diverse software analytics tasks, yet their real-world adoption remains limited by high computational demands, slow inference speeds, significant energy consumption, and…

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowledge discovery. Prior work on automated publication type and study design indexing has…

The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading…

Language detoxification involves removing toxicity from offensive language. While a neutral-toxic paired dataset provides a straightforward approach for training detoxification models, creating such datasets presents several challenges: i)…

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings. To mitigate the limitations of robustness, we introduce a new measure called…

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and…

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

To reduce the toxic degeneration in a pretrained Language Model (LM), previous work on Language Model detoxification has focused on reducing the toxicity of the generation itself (self-toxicity) without consideration of the context. As a…

Text classification methods have been widely investigated as a way to detect content of low credibility: fake news, social media bots, propaganda, etc. Quite accurate models (likely based on deep neural networks) help in moderating public…

We introduce the first study of automatic detoxification of Russian texts to combat offensive language. Such a kind of textual style transfer can be used, for instance, for processing toxic content in social media. While much work has been…

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning…

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…