English
Related papers

Related papers: Selective Safety Steering via Value-Filtered Decod…

200 papers

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

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Computation and Language · Computer Science 2026-03-04 Chung-En Sun , Ge Yan , Zimo Wang , Tsui-Wei Weng

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Computation and Language · Computer Science 2025-10-16 Juan Ren , Mark Dras , Usman Naseem

Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on model uncertainty, meaning an internal estimate of how likely…

Computation and Language · Computer Science 2026-03-04 Mohammad Atif Quamar , Mohammad Areeb , Mikhail Kuznetsov , Muslum Ozgur Ozmen , Z. Berkay Celik

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Ross Greer , Maitrayee Keskar , Angel Martinez-Sanchez , Parthib Roy , Shashank Shriram , Mohan Trivedi

As language models have a greater impact on society, it is important to ensure they are aligned to a diverse range of perspectives and are able to reflect nuance in human values. However, the most popular training paradigms for modern…

Computation and Language · Computer Science 2025-10-21 Chu Fei Luo , Samuel Dahan , Xiaodan Zhu

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Machine Learning · Computer Science 2025-05-22 Tong Wu , Chong Xiang , Jiachen T. Wang , G. Edward Suh , Prateek Mittal

Large Language Models (LLMs) rely on various decoding strategies to generate text, and these choices can significantly affect output quality. In healthcare, where accuracy is critical, the impact of decoding strategies remains…

Computation and Language · Computer Science 2025-08-20 Oriana Presacan , Alireza Nik , Vajira Thambawita , Bogdan Ionescu , Michael Riegler

Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets,…

Artificial Intelligence · Computer Science 2025-05-21 Giannis Chatziveroglou

The autonomous decision-making process, which is increasingly applied to computer systems, requires that the choices made by these systems align with human values. In this context, systems must assess how well their decisions reflect human…

Computers and Society · Computer Science 2025-12-19 Eduardo de la Cruz Fernández , Marcelo Karanik , Sascha Ossowski

Time series anomaly detection is critical for supply chain management to take proactive operations, but faces challenges: classical unsupervised anomaly detection based on exploiting data patterns often yields results misaligned with…

Machine Learning · Computer Science 2026-01-28 Haoting Zhang , Shekhar Jain

Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context of language model safety, when a partial unsafe generation is…

Machine Learning · Computer Science 2024-09-24 Yiming Zhang , Jianfeng Chi , Hailey Nguyen , Kartikeya Upasani , Daniel M. Bikel , Jason Weston , Eric Michael Smith

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

Computation and Language · Computer Science 2025-02-18 Shu Yang , Shenzhe Zhu , Liang Liu , Lijie Hu , Mengdi Li , Di Wang

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…

Machine Learning · Computer Science 2025-05-27 Melis Ilayda Bal , Volkan Cevher , Michael Muehlebach

Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce…

Artificial Intelligence · Computer Science 2026-03-20 Zikang Ding , Qiying Hu , Yi Zhang , Hongji Li , Junchi Yao , Hongbo Liu , Lijie Hu

Large language models are increasingly used in applications where alignment with human values is critical. While model fine-tuning is often employed to ensure safe responses, this technique is static and does not lend itself to everyday…

Computation and Language · Computer Science 2025-11-24 Giulio Antonio Abbo , Tony Belpaeme

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

Computation and Language · Computer Science 2017-11-23 Dinghan Shen , Yizhe Zhang , Ricardo Henao , Qinliang Su , Lawrence Carin
‹ Prev 1 8 9 10 Next ›