Related papers: A Sentence Relation-Based Approach to Sanitizing M…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful content from scratch is more difficult than inducing LLM to…

WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-efficient two-stage framework for explainable content moderation…

High-quality parallel corpora are essential for Machine Translation (MT) research and translation teaching. However, Arabic-English resources remain scarce and existing datasets mainly consist of simple one-to-one mappings. In this paper,…

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…

Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or trained adversarial generators, but are slow,…

We introduce SONAR, a new multilingual and multimodal fixed-size sentence embedding space. Our single text encoder, covering 200 languages, substantially outperforms existing sentence embeddings such as LASER3 and LabSE on the xsim and…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp…

In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution…

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such…

Large Language Models (LLMs) have become integral to Software Engineering (SE), increasingly used in development workflows. However, their widespread adoption raises concerns about the presence and propagation of toxic language - harmful or…

Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and overlook the rich safety-relevant features distributed across…

While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at…

Large language models (LLMs) are increasingly used in sensitive domains, where their ability to infer personal data from seemingly benign text introduces emerging privacy risks. While recent LLM-based anonymization methods help mitigate…

Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…

The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion objectives. We present SONAR-LLM, a decoder-only transformer that…

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and…