Copertina

Concealment of Intent: A Game-Theoretic Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Xinbo, Umrawal, Abhishek, Varshney, Lav R.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Theoretical Game of Attacks via Compositional Skills
di: Wu, Xinbo, et al.
Pubblicazione: (2026)

Transformer-based Causal Language Models Perform Clustering
di: Wu, Xinbo, et al.
Pubblicazione: (2024)

A Meta-Learning Perspective on Transformers for Causal Language Modeling
di: Wu, Xinbo, et al.
Pubblicazione: (2023)

SwitchCIT: Switching for Continual Instruction Tuning
di: Wu, Xinbo, et al.
Pubblicazione: (2024)

Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations
di: Cherukuri, Kalyan, et al.
Pubblicazione: (2026)

A Game-Theoretic Approach to a Task Delegation Problem
di: Dobakhshari, Donya G., et al.
Pubblicazione: (2020)

Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
di: Hartman, Max, et al.
Pubblicazione: (2025)

Efficient Model-Agnostic Multi-Group Equivariant Networks
di: Baltaji, Razan, et al.
Pubblicazione: (2023)

Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
di: Baltaji, Razan, et al.
Pubblicazione: (2024)

Fractional Budget Allocation for Influence Maximization under General Marketing Strategies
di: Bhimaraju, Akhil, et al.
Pubblicazione: (2024)

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
di: Ma, Zihan, et al.
Pubblicazione: (2025)

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning
di: Singhal, Raghav, et al.
Pubblicazione: (2025)

Many LLMs Are More Utilitarian Than One
di: Keshmirian, Anita, et al.
Pubblicazione: (2025)

JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation
di: Huang, Yingbing, et al.
Pubblicazione: (2025)

An Annotated Reading of 'The Singer of Tales' in the LLM Era
di: Varshney, Kush R.
Pubblicazione: (2025)

Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study
di: Baltaji, Razan, et al.
Pubblicazione: (2023)

When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models
di: Zhao, Jiaqi, et al.
Pubblicazione: (2026)

LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation
di: Ye, Yuxiao, et al.
Pubblicazione: (2026)

Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition
di: Yao, Rujing, et al.
Pubblicazione: (2026)

MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability
di: Han, Yikun, et al.
Pubblicazione: (2026)

The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness
di: Varshney, Neeraj, et al.
Pubblicazione: (2023)

Seamless Deception: Larger Language Models Are Better Knowledge Concealers
di: Ashok, Dhananjay, et al.
Pubblicazione: (2026)

CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs
di: Nikeghbal, Nafiseh, et al.
Pubblicazione: (2025)

Linguistic Steganalysis via LLMs: Two Modes for Efficient Detection of Strongly Concealed Stego
di: Tang, Yifan, et al.
Pubblicazione: (2024)

Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition
di: Hengst, Floris den, et al.
Pubblicazione: (2024)

Semantically Grounded QFormer for Efficient Vision Language Understanding
di: Choraria, Moulik, et al.
Pubblicazione: (2023)

IntentGPT: Few-shot Intent Discovery with Large Language Models
di: Rodriguez, Juan A., et al.
Pubblicazione: (2024)

Minimizing PLM-Based Few-Shot Intent Detectors
di: Zhang, Haode, et al.
Pubblicazione: (2024)

Ungraded Assignments in Introductory Computing: A Report
di: Tellawi, Yehya Sleiman, et al.
Pubblicazione: (2025)

DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
di: Choraria, Moulik, et al.
Pubblicazione: (2025)

Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotation
di: Petukhova, Kseniia, et al.
Pubblicazione: (2025)

New Intent Discovery with Pre-training and Contrastive Learning
di: Zhang, Yuwei, et al.
Pubblicazione: (2022)

Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game
di: Karabag, Mustafa O., et al.
Pubblicazione: (2025)

Known Intents, New Combinations: Clause-Factorized Decoding for Compositional Multi-Intent Detection
di: Nandy, Abhilash
Pubblicazione: (2026)

Steering Language Models with Game-Theoretic Solvers
di: Gemp, Ian, et al.
Pubblicazione: (2024)

Reading with Intent -- Neutralizing Intent
di: Reichman, Benjamin, et al.
Pubblicazione: (2025)

Effectiveness of Pre-training for Few-shot Intent Classification
di: Zhang, Haode, et al.
Pubblicazione: (2021)

Intent Detection in the Age of LLMs
di: Arora, Gaurav, et al.
Pubblicazione: (2024)

Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
di: Deng, Yimin, et al.
Pubblicazione: (2024)

LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation
di: Yang, Gao, et al.
Pubblicazione: (2025)