English
Related papers

Related papers: Discovering Forbidden Topics in Language Models

200 papers

Theme detection is a fundamental task in user-centric dialogue systems, aiming to identify the latent topic of each utterance without relying on predefined schemas. Unlike intent induction, which operates within fixed label spaces, theme…

Computation and Language · Computer Science 2025-12-29 Rui Ke , Jiahui Xu , Shenghao Yang , Kuang Wang , Feng Jiang , Haizhou Li

The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…

Cryptography and Security · Computer Science 2025-08-04 Francesco Panebianco , Stefano Bonfanti , Francesco Trovò , Michele Carminati

We ask how to defend user ability to plausibly deny their interest in topics deemed sensitive in the face of search engine learning. We develop a practical and scalable tool called \PDE{} allowing a user to detect and assess threats to…

Cryptography and Security · Computer Science 2017-06-27 Pol Mac Aonghusa , Douglas J. Leith

Open intent classification, which aims to correctly classify the known intents into their corresponding classes while identifying the new unknown (open) intents, is an essential but challenging task in dialogue systems. In this paper, we…

Computation and Language · Computer Science 2023-04-21 Xiaokang Liu , Jianquan Li , Jingjing Mu , Min Yang , Ruifeng Xu , Benyou Wang

Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model…

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Computation and Language · Computer Science 2025-09-26 Manlai Liang , Mandi Liu , Jiangzhou Ji , Huaijun Li , Haobo Yang , Yaohan He , Jinlong Li

Detecting hateful content is a challenging and important problem. Automated tools, like machine-learning models, can help, but they require continuous training to adapt to the ever-changing landscape of social media. In this work, we…

Computation and Language · Computer Science 2025-11-06 Jay Patel , Hrudayangam Mehta , Jeremy Blackburn

Implicit gender bias in Large Language Models (LLMs) is a well-documented problem, and implications of gender introduced into automatic translations can perpetuate real-world biases. However, some LLMs use heuristics or post-processing to…

Computation and Language · Computer Science 2024-04-03 Peter J Barclay , Ashkan Sami

Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent studies have identified various biases that such models exhibit and have proposed methods to correct these biases. However, most of the works address a…

Computation and Language · Computer Science 2024-02-13 Prachi Jain , Ashutosh Sathe , Varun Gumma , Kabir Ahuja , Sunayana Sitaram

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…

Machine Learning · Computer Science 2026-05-27 Youngin Kim , Ray Sun , Inho Kim , Bumsoo Park , Hyun Oh Song

Model interpretability methods are often used to explain NLP model decisions on tasks such as text classification, where the output space is relatively small. However, when applied to language generation, where the output space often…

Computation and Language · Computer Science 2022-05-24 Kayo Yin , Graham Neubig

It is important for Large Language Models (LLMs) to be aware of the boundary of their knowledge, distinguishing queries they can confidently answer from those that lie beyond their capabilities. Such awareness enables models to perform…

Computation and Language · Computer Science 2026-03-05 Lihu Chen , Gerard de Melo , Fabian M. Suchanek , Gaël Varoquaux

As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms. Many datasets for measuring bias currently…

Computation and Language · Computer Science 2022-10-31 Eric Michael Smith , Melissa Hall , Melanie Kambadur , Eleonora Presani , Adina Williams

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Cryptography and Security · Computer Science 2026-03-12 David Campbell , Neil Kale , Udari Madhushani Sehwag , Bert Herring , Nick Price , Dan Borges , Alex Levinson , Christina Q Knight

Among the hardest tasks for humans are those found in competitive programming where problems require sophisticated algorithmic thinking, puzzle solving, and the creation of effective code. As a domain to assess language models (LMs), it has…

Computation and Language · Computer Science 2025-09-03 Md Tanzib Hosain , Md Kishor Morol

Unbiased Learning to Rank (ULTR) that learns to rank documents with biased user feedback data is a well-known challenge in information retrieval. Existing methods in unbiased learning to rank typically rely on click modeling or inverse…

Information Retrieval · Computer Science 2023-02-09 Dan Luo , Lixin Zou , Qingyao Ai , Zhiyu Chen , Dawei Yin , Brian D. Davison

Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We…

Computation and Language · Computer Science 2026-04-27 Max Zhang , Derek Liu , Kai Zhang , Joshua Franco , Haihao Liu

We present an open-source benchmark and evaluation framework for assessing emotional boundary handling in Large Language Models (LLMs). Using a dataset of 1156 prompts across six languages, we evaluated three leading LLMs (GPT-4o,…

Computation and Language · Computer Science 2025-02-24 David Noever , Grant Rosario

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This…

Cryptography and Security · Computer Science 2024-12-03 Jie Li , Yi Liu , Chongyang Liu , Xiaoning Ren , Ling Shi , Weisong Sun , Yinxing Xue

Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, yet they exhibit remarkable reasoning skills. However, the trustworthiness challenges posed by these black-box models have become increasingly evident in…

Computation and Language · Computer Science 2025-08-26 Yunxiao Zhao , Hao Xu , Zhiqiang Wang , Xiaoli Li , Jiye Liang , Ru Li