LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Song, Maojia, Pala, Tej Deep, Zhou, Ruiwen, Jin, Weisheng, Zadeh, Amir, Li, Chuan, Herremans, Dorien, Poria, Soujanya
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference
di: Jin, Weisheng, et al.
Pubblicazione: (2025)

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
di: Pala, Tej Deep, et al.
Pubblicazione: (2025)

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
di: Deep, Pala Tej, et al.
Pubblicazione: (2024)

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
di: Kang, Jaeyong, et al.
Pubblicazione: (2023)

Lessons from Training Grounded LLMs with Verifiable Rewards
di: Sim, Shang Hong, et al.
Pubblicazione: (2025)

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
di: Pala, Tej Deep, et al.
Pubblicazione: (2024)

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
di: Ong, Brandon, et al.
Pubblicazione: (2025)

Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics
di: Song, Maojia, et al.
Pubblicazione: (2025)

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
di: Hung, Chia-Yu, et al.
Pubblicazione: (2025)

Mustango: Toward Controllable Text-to-Music Generation
di: Melechovsky, Jan, et al.
Pubblicazione: (2023)

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
di: Sun, Qi, et al.
Pubblicazione: (2024)

JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
di: Liu, Renhang, et al.
Pubblicazione: (2025)

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
di: Song, Maojia, et al.
Pubblicazione: (2024)

Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges
di: Kang, Jaeyong, et al.
Pubblicazione: (2024)

DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage
di: Wang, Kyra, et al.
Pubblicazione: (2024)

PreBit -- A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin
di: Zou, Yanzhao, et al.
Pubblicazione: (2022)

Towards Unified Music Emotion Recognition across Dimensional and Categorical Models
di: Kang, Jaeyong, et al.
Pubblicazione: (2025)

Aligning Generative Music AI with Human Preferences: Methods and Challenges
di: Herremans, Dorien, et al.
Pubblicazione: (2025)

DeepUnifiedMom: Unified Time-series Momentum Portfolio Construction via Multi-Task Learning with Multi-Gate Mixture of Experts
di: Ong, Joel, et al.
Pubblicazione: (2024)

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
di: Lei, Jingdi, et al.
Pubblicazione: (2025)

Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
di: Zhou, Ruiwen, et al.
Pubblicazione: (2026)

APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
di: Husain, Jaavid Aktar, et al.
Pubblicazione: (2026)

Forecasting Bitcoin volatility spikes from whale transactions and CryptoQuant data using Synthesizer Transformer models
di: Herremans, Dorien, et al.
Pubblicazione: (2022)

When Drawing Is Not Enough: Exploring Spontaneous Speech with Sketch for Intent Alignment in Multimodal LLMs
di: Shi, Weiyan, et al.
Pubblicazione: (2026)

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
di: Hung, Chia-Yu, et al.
Pubblicazione: (2025)

KARMA-MV: A Benchmark for Causal Question Answering on Music Videos
di: Ghosh, Archishman, et al.
Pubblicazione: (2026)

BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Features
di: Luo, Jing, et al.
Pubblicazione: (2024)

Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction
di: Liu, Renhang, et al.
Pubblicazione: (2024)

Digital Lifelong Learning in the Age of AI: Trends and Insights
di: Puri, Geeta, et al.
Pubblicazione: (2026)

MidiCaps: A large-scale MIDI dataset with text captions
di: Melechovsky, Jan, et al.
Pubblicazione: (2024)

MIRFLEX: Music Information Retrieval Feature Library for Extraction
di: Chopra, Anuradha, et al.
Pubblicazione: (2024)

Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction
di: Wickramasinghe, Sithumi, et al.
Pubblicazione: (2025)

MERIT: Learning Disentangled Music Representations for Audio Similarity
di: Roy, Abhinaba, et al.
Pubblicazione: (2026)

SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning
di: Chopra, Anuradha, et al.
Pubblicazione: (2025)

Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment
di: Roy, Abhinaba, et al.
Pubblicazione: (2025)

To Embody or Not: The Effect Of Embodiment On User Perception Of LLM-based Conversational Agents
di: Wang, Kyra, et al.
Pubblicazione: (2025)

Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
di: Chia, Yew Ken, et al.
Pubblicazione: (2024)

Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
di: Lei, Jingdi, et al.
Pubblicazione: (2025)

Towards Robust Instruction Tuning on Multimodal Large Language Models
di: Han, Wei, et al.
Pubblicazione: (2024)

PREMISE: Matching-based Prediction for Accurate Review Recommendation
di: Han, Wei, et al.
Pubblicazione: (2025)