English
Related papers

Related papers: Epistemic Traps: Rational Misalignment Driven by M…

200 papers

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…

Computation and Language · Computer Science 2026-01-21 Xuhao Hu , Peng Wang , Xiaoya Lu , Dongrui Liu , Xuanjing Huang , Jing Shao

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…

Machine Learning · Computer Science 2018-11-20 Jan Leike , David Krueger , Tom Everitt , Miljan Martic , Vishal Maini , Shane Legg

The high-order complexity of human behaviour is likely the root cause of extreme difficulty in financial market projections. We consider that behavioural simulation can unveil systemic dynamics to support analysis. Simulating diverse human…

Trading and Market Microstructure · Quantitative Finance 2025-06-03 Cheng Wang , Chuwen Wang , Shirong Zeng , Jianguo Liu , Changjun Jiang

Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game" training signals, performing misbehaviors those signals…

Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally…

Machine Learning · Computer Science 2026-01-05 Laksh Advani

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are…

Computation and Language · Computer Science 2026-01-27 Jan Betley , Daniel Tan , Niels Warncke , Anna Sztyber-Betley , Xuchan Bao , Martín Soto , Nathan Labenz , Owain Evans

Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…

Cryptography and Security · Computer Science 2026-05-01 Andrei Kojukhov , Arkady Bovshover

Spatial reasoning in partially observable environments has often been approached through passive predictive models, yet theories of embodied cognition suggest that genuinely useful representations arise only when perception is tightly…

Artificial Intelligence · Computer Science 2025-04-29 Li Jin , Liu Jia

This work suggests modifications to a previously introduced class of heterogeneous agent models that allow for the inclusion of different types of agent motivations and behaviours in a unified way. The agents operate within a highly…

Trading and Market Microstructure · Quantitative Finance 2009-11-13 H. Lamba , T. Seaman

The rapid evolution of agentic AI marks a new phase in artificial intelligence, where Large Language Models (LLMs) no longer merely respond but act, reason, and adapt. This survey traces the paradigm shift in building agentic AI: from…

Artificial Intelligence · Computer Science 2025-10-28 Jitao Sang , Jinlin Xiao , Jiarun Han , Jilin Chen , Xiaoyi Chen , Shuyu Wei , Yongjie Sun , Yuhang Wang

With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency, which remains understudied. Epistemic agency, the ability to…

Artificial Intelligence · Computer Science 2025-06-05 Lingyu Li , Yixu Wang , Haiquan Zhao , Shuqi Kong , Yan Teng , Chunbo Li , Yingchun Wang

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values and ethical norms, a…

Computation and Language · Computer Science 2026-01-27 Chen Chen , Kim Young Il , Yuan Yang , Wenhao Su , Yilin Zhang , Xueluan Gong , Qian Wang , Yongsen Zheng , Ziyao Liu , Kwok-Yan Lam

Current labor markets are strongly affected by the economic forces of adverse selection, moral hazard, and reputation, each of which arises due to $\textit{incomplete information}$. These economic forces will still be influential after AI…

Artificial Intelligence · Computer Science 2025-05-27 Simpson Zhang , Tennison Liu , Mihaela van der Schaar

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure…

Cryptography and Security · Computer Science 2026-03-18 Pengcheng Li , Jie Zhang , Tianwei Zhang , Han Qiu , Zhang kejun , Weiming Zhang , Nenghai Yu , Wenbo Zhou

Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic adaptation as gaming and attempted to mitigate its effects,…

Machine Learning · Computer Science 2020-02-19 John Miller , Smitha Milli , Moritz Hardt

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

Computation and Language · Computer Science 2025-06-06 Raphaël Millière

Decisions based partly or solely on predictions from probabilistic models may be sensitive to model misspecification. Statisticians are taught from an early stage that "all models are wrong", but little formal guidance exists on how to…

Methodology · Statistics 2015-03-09 James Watson , Chris Holmes

Present bias, the tendency to weigh costs and benefits incurred in the present too heavily, is one of the most widespread human behavioral biases. It has also been the subject of extensive study in the behavioral economics literature. While…

Computer Science and Game Theory · Computer Science 2016-03-29 Jon Kleinberg , Sigal Oren , Manish Raghavan

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors…

Cryptography and Security · Computer Science 2026-05-25 Tanzim Ahad , Ismail Hossain , Md Jahangir Alam , Sai Puppala , Syed Bahauddin Alam , Sajedul Talukder

Understanding the decisions made and actions taken by increasingly complex AI system remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of…

‹ Prev 1 8 9 10 Next ›