相关论文: Speculating LLMs' Chinese Training Data Pollution …

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Large Language Models (LLMs), such as GPT, are considered to learn the latent distributions within large-scale web-crawl datasets and accomplish natural language processing (NLP) tasks by predicting the next token. However, this mechanism…

Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data…

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

This work quantifies the risk of training data leakage from LLMs (Large Language Models) using sequence-level probabilities. Computing extraction probabilities for individual sequences provides finer-grained information than has been…

Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of…

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

Context: Large Language Models (LLMs) like GPT-5 and LLaMA-405b exhibit advanced code generation abilities, but their deployment demands substantial computation resources and energy. Quantization can reduce memory footprint and hardware…

In this study, we introduce CT-LLM, a 2B large language model (LLM) that illustrates a pivotal shift towards prioritizing the Chinese language in developing LLMs. Uniquely initiated from scratch, CT-LLM diverges from the conventional…

We present a systematic study of provider-side data poisoning in retrieval-augmented recommender systems (RAG-based). By modifying only a small fraction of tokens within item descriptions -- for instance, adding emotional keywords or…

Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot of attention due to the capacity of few-shot (even zero-shot)…

The hallucination and credibility concerns of large language models (LLMs) are global challenges that the industry is collectively addressing. Recently, a significant amount of advances have been made on post-training and inference…

As the scale of training corpora for large language models (LLMs) grows, model developers become increasingly reluctant to disclose details on their data. This lack of transparency poses challenges to scientific evaluation and ethical…

We present a controlled study of how dataset contamination interacts with the post-training stages now standard in large language model training pipelines. Starting from clean checkpoints of Qwen2.5 (0.5B/1.5B) and Gemma3 (1B/4B), we inject…

Dominant pre-trained language models (PLMs) have demonstrated the potential risk of memorizing and outputting the training data. While this concern has been discussed mainly in English, it is also practically important to focus on…

The rapid development of large language models (LLMs) gives rise to ethical concerns about their performance, while opening new avenues for developing toxic language detection techniques. However, LLMs' unethical output and their capability…

Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for…

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise to the partial token problem, which occurs when a user ends their prompt in the middle of the expected…

Large language models (LLMs) have become ubiquitous, interfacing with humans in numerous safety-critical applications. This necessitates improving capabilities, but importantly coupled with greater safety measures to align these models with…