Cover Image

Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Chloe, Phuong, Mary, Tan, Daniel
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
by: Li, Chloe, et al.
Published: (2025)

Benchmarking Concept-Spilling Across Languages in LLMs
by: Badanin, Ilia, et al.
Published: (2026)

Spill The Beans: Exploiting CPU Cache Side-Channels to Leak Tokens from Large Language Models
by: Adiletta, Andrew, et al.
Published: (2025)

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
by: Qi, Zhenting, et al.
Published: (2024)

Capability Self-Assessment: Teaching LLMs to Know Their Limits
by: Yang, Haoyan, et al.
Published: (2026)

From Stability to Inconsistency: A Study of Moral Preferences in LLMs
by: Jotautaite, Monika, et al.
Published: (2025)

Spilled Energy in Large Language Models
by: Minut, Adrian Robert, et al.
Published: (2026)

Tricking LLM-Based NPCs into Spilling Secrets
by: Shiomi, Kyohei, et al.
Published: (2025)

Teaching LLMs to Ask: Self-Querying Category-Theoretic Planning for Under-Specified Reasoning
by: Qu, Shuhui
Published: (2026)

On the Hidden Objective Biases of Group-based Reinforcement Learning
by: Fontana, Aleksandar, et al.
Published: (2026)

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
by: Xu, Tianyang, et al.
Published: (2024)

Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs
by: Yan, Qianqi, et al.
Published: (2025)

MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
by: Huang, Yue, et al.
Published: (2025)

How to Assess AI Literacy: Misalignment Between Self-Reported and Objective-Based Measures
by: Zhang, Shan, et al.
Published: (2026)

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
by: Li, Mingjie, et al.
Published: (2026)

Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries
by: Yu, Jiahao, et al.
Published: (2024)

When Speculation Spills Secrets: Side Channels via Speculative Decoding In LLMs
by: Wei, Jiankun, et al.
Published: (2024)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
by: Lu, Yu-An, et al.
Published: (2026)

Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning
by: Li, Xinran, et al.
Published: (2025)

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
by: Zhang, Jin, et al.
Published: (2025)

The Challenge of Teaching Reasoning to LLMs Without RL or Distillation
by: Du, Wei, et al.
Published: (2025)

Oil Spill Segmentation using Deep Encoder-Decoder models
by: Satyanarayana, Abhishek Ramanathapura, et al.
Published: (2023)

Self-Routing: Parameter-Free Expert Routing from Hidden States
by: Mohamud, Jama Hussein, et al.
Published: (2026)

Measuring Teaching with LLMs
by: Hardy, Michael
Published: (2025)

Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find
by: Bianchi, Owen, et al.
Published: (2025)

G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
by: Guo, Xiaojun, et al.
Published: (2025)

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
by: Yuan, Huining, et al.
Published: (2025)

Estimating the Self-Consistency of LLMs
by: Nowak, Robert
Published: (2025)

Structure Enables Effective Self-Localization of Errors in LLMs
by: Samanta, Ankur, et al.
Published: (2026)

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
by: Yang, Rui, et al.
Published: (2024)

Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoning
by: Draganov, Andrew, et al.
Published: (2026)

CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO
by: Li, Yang, et al.
Published: (2026)

MEMENTO: Teaching LLMs to Manage Their Own Context
by: Kontonis, Vasilis, et al.
Published: (2026)

From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs
by: Wang, Xiaoxuan, et al.
Published: (2025)

Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
by: Teo, Rachel S. Y., et al.
Published: (2024)

Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models
by: Polowczyk, Agnieszka, et al.
Published: (2025)

Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization
by: Yu, Jiajun, et al.
Published: (2025)

Introspection Adapters: Training LLMs to Report Their Learned Behaviors
by: Shenoy, Keshav, et al.
Published: (2026)

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
by: Hu, Jinchao, et al.
Published: (2026)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
by: Lee, Jihoon, et al.
Published: (2025)