English
Related papers

Related papers: SCAR: Sparse Conditioned Autoencoders for Concept …

200 papers

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Computation and Language · Computer Science 2026-01-13 Jinyi Han , Zixiang Di , Zishang Jiang , Ying Liao , Jiaqing Liang , Yongqi Wang , Yanghua Xiao

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Machine Learning · Computer Science 2025-08-07 Gonçalo Paulo , Alex Mallen , Caden Juang , Nora Belrose

Large Language Models (LLMs) have revolutionised the field of Natural Language Processing (NLP) and have achieved state-of-the-art performance in practically every task in this field. However, the prevalent approach used in text generation,…

Computation and Language · Computer Science 2024-08-12 Nicolo Micheletti , Samuel Belkadi , Lifeng Han , Goran Nenadic

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives…

Machine Learning · Computer Science 2025-07-01 Kenny Peng , Rajiv Movva , Jon Kleinberg , Emma Pierson , Nikhil Garg

Reliable collision avoidance under extreme situations remains a critical challenge for autonomous vehicles. While large language models (LLMs) offer promising reasoning capabilities, their application in safety-critical evasive maneuvers is…

Robotics · Computer Science 2025-06-12 Shiyue Zhao , Junzhi Zhang , Neda Masoud , Heye Huang , Xiaohui Hou , Chengkun He

The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter…

Computation and Language · Computer Science 2024-06-06 Zheyuan Liu , Guangyao Dou , Zhaoxuan Tan , Yijun Tian , Meng Jiang

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…

Computation and Language · Computer Science 2024-10-03 Amrita Bhattacharjee , Shaona Ghosh , Traian Rebedea , Christopher Parisien

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

Computation and Language · Computer Science 2020-09-29 Samuel Gehman , Suchin Gururangan , Maarten Sap , Yejin Choi , Noah A. Smith

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Artificial Intelligence · Computer Science 2024-12-18 Zouying Cao , Yifei Yang , Hai Zhao

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

Ensuring the safety of autonomous vehicles requires virtual scenario-based testing, which depends on the robust evaluation and generation of safety-critical scenarios. So far, researchers have used scenario-based testing frameworks that…

Artificial Intelligence · Computer Science 2025-07-21 Yuan Gao , Mattia Piccinini , Korbinian Moller , Amr Alanwar , Johannes Betz

How should one judge whether a given large language model (LLM) can reliably perform economic reasoning? Most existing LLM benchmarks focus on specific applications and fail to present the model with a rich variety of economic tasks. A…

Computation and Language · Computer Science 2025-02-20 Narun Raman , Taylor Lundy , Thiago Amin , Jesse Perla , Kevin Leyton-Brown

Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ryan Xu , Dongyang Jin , Yancheng Bai , Rui Lan , Xu Duan , Lei Sun , Xiangxiang Chu

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

Machine Learning · Computer Science 2025-11-04 Samaksh Bhargav , Zining Zhu

Large Language Models have found success in a variety of applications. However, their safety remains a concern due to the existence of various jailbreaking methods. Despite significant efforts, alignment and safety fine-tuning only provide…

Computation and Language · Computer Science 2025-12-16 Darpan Aswal , Céline Hudelot

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…

Computation and Language · Computer Science 2026-02-09 Himanshu Singh , Ziwei Xu , A. V. Subramanyam , Mohan Kankanhalli

Autonomous Driving Systems (ADS) require diverse and safety-critical traffic scenarios for effective training and testing, but the existing data generation methods struggle to provide flexibility and scalability. We propose LASER, a novel…

Robotics · Computer Science 2024-10-25 Hao Gao , Jingyue Wang , Wenyang Fang , Jingwei Xu , Yunpeng Huang , Taolue Chen , Xiaoxing Ma

We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-organize, using only minimal supervision (labels for <0.1% of examples per anchored concept).…

Machine Learning · Computer Science 2026-04-28 Sandy Fraser , Patryk Wielopolski

The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents…

Computation and Language · Computer Science 2025-08-25 Doohee You , Andy Parisi , Zach Vander Velden , Lara Dantas Inojosa

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

Computation and Language · Computer Science 2025-09-16 Yi Jing , Zijun Yao , Hongzhu Guo , Lingxu Ran , Xiaozhi Wang , Lei Hou , Juanzi Li
‹ Prev 1 4 5 6 7 8 10 Next ›