Imagen de Portada

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiao, Hanqi, Patil, Vaidehi, Khan, Zaid, Lee, Hyunji, Stengel-Eskin, Elias, Bansal, Mohit
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns
por: Xiao, Hanqi, et al.
Publicado: (2025)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
por: Patil, Vaidehi, et al.
Publicado: (2025)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
por: Patil, Vaidehi, et al.
Publicado: (2025)

Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
por: Singh, Joykirat, et al.
Publicado: (2026)

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
por: Khan, Zaid, et al.
Publicado: (2024)

Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
por: Nguyen, Duy, et al.
Publicado: (2026)

Multi-Attribute Steering of Language Models via Targeted Intervention
por: Nguyen, Duy, et al.
Publicado: (2025)

One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
por: Khan, Zaid, et al.
Publicado: (2025)

Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression
por: Xiao, Hanqi, et al.
Publicado: (2025)

AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
por: Nguyen, Duy, et al.
Publicado: (2026)

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
por: Khan, Zaid, et al.
Publicado: (2025)

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
por: Nguyen, Duy, et al.
Publicado: (2025)

ReGAL: Refactoring Programs to Discover Generalizable Abstractions
por: Stengel-Eskin, Elias, et al.
Publicado: (2024)

Learning to Generate Unit Tests for Automated Debugging
por: Prasad, Archiki, et al.
Publicado: (2025)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
por: Stengel-Eskin, Elias, et al.
Publicado: (2024)

Teaching Models to Balance Resisting and Accepting Persuasion
por: Stengel-Eskin, Elias, et al.
Publicado: (2024)

Language Models Identify Ambiguities and Exploit Loopholes
por: Choi, Jio, et al.
Publicado: (2025)

Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?
por: Hase, Peter, et al.
Publicado: (2024)

Soft Self-Consistency Improves Language Model Agents
por: Wang, Han, et al.
Publicado: (2024)

Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution
por: Sivakumaran, Nithin, et al.
Publicado: (2026)

Multimodal Fact-Level Attribution for Verifiable Reasoning
por: Wan, David, et al.
Publicado: (2026)

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
por: Prasad, Archiki, et al.
Publicado: (2023)

LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits
por: Nguyen, Duy, et al.
Publicado: (2024)

PRInTS: Reward Modeling for Long-Horizon Information Seeking
por: Lee, Jaewoo, et al.
Publicado: (2025)

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
por: Wang, Han, et al.
Publicado: (2024)

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
por: Pothiraj, Atin, et al.
Publicado: (2025)

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
por: Chen, Justin Chih-Yao, et al.
Publicado: (2024)

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration
por: Wan, David, et al.
Publicado: (2025)

Are language models rational? The case of coherence norms and belief revision
por: Hofweber, Thomas, et al.
Publicado: (2024)

Retrieval-Augmented Generation with Conflicting Evidence
por: Wang, Han, et al.
Publicado: (2025)

RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
por: Niu, Tianyi, et al.
Publicado: (2025)

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
por: Chen, Justin Chih-Yao, et al.
Publicado: (2026)

Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training
por: Wan, David, et al.
Publicado: (2024)

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
por: Chen, Justin Chih-Yao, et al.
Publicado: (2024)

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
por: Ananthram, Amith, et al.
Publicado: (2024)

GenerationPrograms: Fine-grained Attribution with Executable Programs
por: Wan, David, et al.
Publicado: (2025)

CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
por: Wan, David, et al.
Publicado: (2025)

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
por: Chen, Justin Chih-Yao, et al.
Publicado: (2025)

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
por: Singh, Joykirat, et al.
Publicado: (2025)

LAQuer: Localized Attribution Queries in Content-grounded Generation
por: Hirsch, Eran, et al.
Publicado: (2025)