Image de couverture de livre

Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shi, Jerick, Zhang, Terry Jingcheng, Jin, Zhijing, Conitzer, Vincent
Format:	Preprint
Publié:	2026
Sujets:	Computers and Society
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From Hallucination to Scheming: A Unified Taxonomy and Benchmark Analysis for LLM Deception
par: Shi, Jerick, et autres
Publié: (2026)

Cheap Talk
par: St. Pierre, Joshua
Publié: (2025)

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
par: Tewolde, Emanuel, et autres
Publié: (2026)

Predictive Power of LLMs in Financial Markets
par: Shi, Jerick, et autres
Publié: (2024)

Causality for Natural Language Processing
par: Jin, Zhijing
Publié: (2025)

Now, Later, and Lasting: Ten Priorities for AI Research, Policy, and Practice
par: Horvitz, Eric, et autres
Publié: (2024)

Evaluating the Promise and Pitfalls of LLMs in Hiring Decisions
par: Anzenberg, Eitan, et autres
Publié: (2025)

The Promises and Perils of using LLMs for Effective Public Services
par: Moon, Erina Seh-Young, et autres
Publié: (2026)

On the Pros and Cons of Active Learning for Moral Preference Elicitation
par: Keswani, Vijay, et autres
Publié: (2024)

Market-Dependent Communication in Multi-Agent Alpha Generation
par: Shi, Jerick, et autres
Publié: (2025)

Assessing Large Language Models' ability to predict how humans balance self-interest and the interest of others
par: Capraro, Valerio, et autres
Publié: (2023)

The promise and perils of AI in medicine
par: Sparrow, Robert, et autres
Publié: (2025)

Cheap Expertise: Mapping and Challenging Industry Perspectives in the Expert Data Gig Economy
par: Wolfe, Robert, et autres
Publié: (2026)

Algorithmic Cheap Talk
par: Babichenko, Yakov, et autres
Publié: (2023)

Equitable Access to Justice: Logical LLMs Show Promise
par: Kant, Manuj, et autres
Publié: (2024)

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
par: Cobben, Pepijn, et autres
Publié: (2026)

Cheap Talk in Bilateral Trade
par: Tucker-Foltz, Jamie, et autres
Publié: (2026)

Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
par: Chen, Sirui, et autres
Publié: (2025)

The Complexity of Computing Robust Mediated Equilibria in Ordinal Games
par: Conitzer, Vincent
Publié: (2024)

Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions
par: Keswani, Vijay, et autres
Publié: (2025)

Gender inequality and self-publication patterns among scientific editors
par: Liu, Fengyuan, et autres
Publié: (2022)

Are LLMs Court-Ready? Evaluating Frontier Models on Indian Legal Reasoning
par: Juvekar, Kush, et autres
Publié: (2025)

Frontier AI systems have surpassed the self-replicating red line
par: Pan, Xudong, et autres
Publié: (2024)

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models
par: Choi, Younwoo, et autres
Publié: (2025)

Can LLMs Talk 'Sex'? Exploring How AI Models Handle Intimate Conversations
par: Lai, Huiqian
Publié: (2025)

An evidence-based and critical analysis of the Fediverse decentralization promises
par: Xavier, Henrique S.
Publié: (2024)

WHBench: Evaluating Frontier LLMs with Expert-in-the-Loop Validation on Women's Health Topics
par: Maurya, Sneha, et autres
Publié: (2026)

On The Stability of Moral Preferences: A Problem with Computational Elicitation Methods
par: Boerstler, Kyle, et autres
Publié: (2024)

Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback
par: Keswani, Vijay, et autres
Publié: (2025)

Talking the Talk Does Not Entail Walking the Walk: On the Limits of Large Language Models in Lexical Entailment Recognition
par: Greco, Candida M., et autres
Publié: (2024)

The California Report on Frontier AI Policy
par: Bommasani, Rishi, et autres
Publié: (2025)

Estimating household contact matrices structure from easily collectable metadata
par: Dall'Amico, Lorenzo, et autres
Publié: (2022)

Online Political Microtargeting: Promises and Threats for Democracy
par: Borgesius, Frederik J. Zuiderveen, et autres
Publié: (2025)

Towards Frontier Safety Policies Plus
par: Pistillo, Matteo
Publié: (2025)

Breaking the ICE: Exploring promises and challenges of benchmarks for Inference Carbon & Energy estimation for LLMs
par: Sikand, Samarth, et autres
Publié: (2025)

Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework
par: Krishna, Satyapriya, et autres
Publié: (2025)

Frontier AI's Impact on the Cybersecurity Landscape
par: Potter, Yujin, et autres
Publié: (2025)

Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models
par: Ortu, Francesco, et autres
Publié: (2026)

When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
par: Backmann, Steffen, et autres
Publié: (2025)

Evaluating AI Providers' Frontier Safety Frameworks
par: Stelling, Lily, et autres
Publié: (2025)