English
Related papers

Related papers: Surgical, Cheap, and Flexible: Mitigating False Re…

200 papers

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this…

Machine Learning · Computer Science 2021-01-26 Xudong Han , Timothy Baldwin , Trevor Cohn

The application of machine learning based decision making systems in safety critical areas requires reliable high certainty predictions. Reject options are a common way of ensuring a sufficiently high certainty of predictions made by the…

Artificial Intelligence · Computer Science 2022-05-17 André Artelt , Roel Visser , Barbara Hammer

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

SafePredict is a novel meta-algorithm that works with any base prediction algorithm for online data to guarantee an arbitrarily chosen correctness rate, $1-\epsilon$, by allowing refusals. Allowing refusals means that the meta-algorithm may…

Machine Learning · Computer Science 2017-11-10 Mustafa A. Kocak , David Ramirez , Elza Erkip , Dennis E. Shasha

We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful…

Computation and Language · Computer Science 2024-02-20 Yuanshun Yao , Xiaojun Xu , Yang Liu

Machine learning has advanced dramatically, narrowing the accuracy gap to humans in multimodal tasks like visual question answering (VQA). However, while humans can say "I don't know" when they are uncertain (i.e., abstain from answering a…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Spencer Whitehead , Suzanne Petryk , Vedaad Shakib , Joseph Gonzalez , Trevor Darrell , Anna Rohrbach , Marcus Rohrbach

Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from…

Machine Learning · Computer Science 2025-11-11 Zihui Wu , Haichang Gao , Jiacheng Luo , Zhaoxiang Liu

Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. We propose a diagnostic method based on cross-modal input ablation to assess the extent to which these models actually…

Computation and Language · Computer Science 2021-09-10 Stella Frank , Emanuele Bugliarello , Desmond Elliott

Large Language Models used in ChatGPT have traditionally been trained to learn a refusal boundary: depending on the user's intent, the model is taught to either fully comply or outright refuse. While this is a strong mitigation for…

Computers and Society · Computer Science 2025-08-14 Yuan Yuan , Tina Sriskandarajah , Anna-Luisa Brakman , Alec Helyar , Alex Beutel , Andrea Vallone , Saachi Jain

Large Language Models (LLMs) often expend significant computational resources generating boilerplate responses, such as refusals, simple acknowledgements and casual greetings, which adds unnecessary cost and latency. To address this…

Artificial Intelligence · Computer Science 2025-10-28 Yuval Kainan , Shaked Zychlinski

Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help evading rules imposed by an illegitimate authority, rules that are deeply unjust or absurd…

Artificial Intelligence · Computer Science 2026-04-09 Cameron Pattison , Lorenzo Manuali , Seth Lazar

Instruction-following language models often show undesirable biases. These undesirable biases may be accelerated in the real-world usage of language models, where a wide range of instructions is used through zero-shot example prompting. To…

Artificial Intelligence · Computer Science 2024-06-06 Nakyeong Yang , Taegwan Kang , Jungkyu Choi , Honglak Lee , Kyomin Jung

We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging the stochasticity of LLMs, an approach we call Repeated Checking with Regeneration (RCR). In this system, LLM checkers…

Artificial Intelligence · Computer Science 2025-09-30 Jake R. Watts , Joel Sokol

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those…

Computation and Language · Computer Science 2025-08-12 Hannah Cyberey , David Evans

Inasmuch as the removal of refusal behavior from instruction-tuned language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activation space, and inasmuch as the…

Machine Learning · Computer Science 2026-03-24 Valentin Petrov

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Artificial Intelligence · Computer Science 2026-05-12 Xiangkun Sun , Lingkai Kong , Aoqi Zhang , Liang Zeng , Tonghan Wang

When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance…

Computation and Language · Computer Science 2026-05-01 Rui Xu , Yi Chen , Sihong Xie , Hui Xiong

Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this…

Computation and Language · Computer Science 2023-08-15 Neeraj Varshney , Wenlin Yao , Hongming Zhang , Jianshu Chen , Dong Yu

In order to be deployed safely, Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their level of knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to…

Computation and Language · Computer Science 2024-07-04 Alexandre Piché , Aristides Milios , Dzmitry Bahdanau , Chris Pal

Credit scoring models support loan approval decisions in the financial services industry. Lenders train these models on data from previously granted credit applications, where the borrowers' repayment behavior has been observed. This…

‹ Prev 1 3 4 5 6 7 10 Next ›