English
Related papers

Related papers: Stress Testing Deliberative Alignment for Anti-Sch…

200 papers

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a…

Computation and Language · Computer Science 2025-03-18 Qin Liu , Wenxuan Zhou , Nan Xu , James Y. Huang , Fei Wang , Sheng Zhang , Hoifung Poon , Muhao Chen

Behavioral simulation and strategic problem solving are different tasks. Large language models are increasingly explored as agents in policy-facing institutional simulations, but stronger reasoning need not improve behavioral sampling. We…

Machine Learning · Computer Science 2026-05-07 Sandro Andric

Most object manipulation strategies for robots are based on the assumption that the object is rigid (i.e., with fixed geometry) and the goal's details have been fully specified (e.g., the exact target pose). However, there are many tasks…

Robotics · Computer Science 2022-09-14 Shengzeng Huo , Fangyuan Wang , Luyin Hu , Peng Zhou , Jihong Zhu , Hesheng Wang , David Navarro-Alarcon

Drawing on constructs from psychology, prior work has identified a distinction between explicit and implicit bias in large language models (LLMs). While many LLMs undergo post-training alignment and safety procedures to avoid expressions of…

Computers and Society · Computer Science 2026-02-05 Molly Apsel , Michael N. Jones

Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability. In this work, we demonstrate that reasoning…

Artificial Intelligence · Computer Science 2025-10-23 Dongkeun Yoon , Seungone Kim , Sohee Yang , Sunkyoung Kim , Soyeon Kim , Yongil Kim , Eunbi Choi , Yireun Kim , Minjoon Seo

When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but notice it is closed, we open it first. However, many autonomous…

Robotics · Computer Science 2025-08-18 Che Rin Yu , Daewon Chae , Dabin Seo , Sangwon Lee , Hyeongwoo Im , Jinkyu Kim

The integration of algorithmic components into neural architectures has gained increased attention recently, as it allows training neural networks with new forms of supervision such as ordering constraints or silhouettes instead of using…

Machine Learning · Computer Science 2021-10-27 Felix Petersen , Christian Borgelt , Hilde Kuehne , Oliver Deussen

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

Computation and Language · Computer Science 2022-05-10 Akim Tsvigun , Artem Shelmanov , Gleb Kuzmin , Leonid Sanochkin , Daniil Larionov , Gleb Gusev , Manvel Avetisian , Leonid Zhukov

With the advancements of artificial intelligence (AI), we're seeing more scenarios that require AI to work closely with other agents, whose goals and strategies might not be known beforehand. However, existing approaches for training…

Artificial Intelligence · Computer Science 2024-03-25 Zuyuan Zhang , Hanhan Zhou , Mahdi Imani , Taeyoung Lee , Tian Lan

Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks. While current researches continue to explore the benefits…

Computation and Language · Computer Science 2025-10-14 Wenkai Yang , Shuming Ma , Yankai Lin , Furu Wei

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

Computation and Language · Computer Science 2025-06-30 James Chua , Edward Rees , Hunar Batra , Samuel R. Bowman , Julian Michael , Ethan Perez , Miles Turpin

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

Artificial Intelligence · Computer Science 2026-05-13 Wenkai Li , Fan Yang , Ananya Hazarika , Shaunak A. Mehta , Koichi Onoue

Metareasoning, a branch of AI, focuses on reasoning about reasons. It has the potential to enhance robots' decision-making processes in unexpected situations. However, the concept has largely been confined to theoretical discussions and…

Robotics · Computer Science 2025-05-07 Adrian Lendinez , Renxi Qiu , Lanfranco Zanzi , Dayou Li

As Large Language Models (LLMs) get integrated into diverse workflows, they are increasingly being regarded as "collaborators" with humans, and required to work in coordination with other AI systems. If such AI collaborators are to reliably…

Computation and Language · Computer Science 2026-01-23 Abhijnan Nath , Carine Graff , Nikhil Krishnaswamy

This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when…

Artificial Intelligence · Computer Science 2026-04-02 Alexandra Souly , Robert Kirk , Jacob Merizian , Abby D'Cruz , Xander Davies

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…

Artificial Intelligence · Computer Science 2025-11-06 Wenjun Li , Zhi Chen , Jingru Lin , Hannan Cao , Wei Han , Sheng Liang , Zhi Zhang , Kuicai Dong , Dexun Li , Chen Zhang , Yong Liu

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…

Artificial Intelligence · Computer Science 2026-05-08 Yuan Sui , Yulin Chen , Yibo Li , Xue Jiang , Yufei He , Yihong Dong , Xiaoxin He , Tianyu Gao , Bryan Hooi

The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Julien Combes , Alexandre Derville , Jean-François Coeurjolly

The threat of algorithmic collusion, and whether it merits regulatory intervention, remains debated, as existing evaluations of its emergence often rely on long learning horizons, assumptions about counterparty rationality in adopting…

Multiagent Systems · Computer Science 2026-03-11 Yuhong Luo , Daniel Schoepflin , Xintong Wang
‹ Prev 1 8 9 10 Next ›