Cover Image

Do LLMs "Feel"? Emotion Circuits Discovery and Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chenxi, Zhang, Yixuan, Yu, Ruiji, Zheng, Yufei, Gao, Lang, Song, Zirui, Xu, Zixiang, Xia, Gus, Zhang, Huishuai, Zhao, Dongyan, Chen, Xiuying
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
by: Wang, Chenxi, et al.
Published: (2025)

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
by: Gao, Lang, et al.
Published: (2025)

Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia
by: Wang, Chenxi, et al.
Published: (2025)

Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies
by: Song, Zirui, et al.
Published: (2025)

Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering
by: Du, Haowei, et al.
Published: (2024)

DyFlow: Dynamic Workflow Framework for Agentic Reasoning
by: Wang, Yanbo, et al.
Published: (2025)

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
by: Song, Zirui, et al.
Published: (2025)

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

Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
by: Gong, Zhuocheng, et al.
Published: (2025)

Efficient Continual Pre-training by Mitigating the Stability Gap
by: Guo, Yiduo, et al.
Published: (2024)

ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
by: Wang, Yueqian, et al.
Published: (2025)

Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
by: Wang, Yueqian, et al.
Published: (2024)

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
by: Gao, Lang, et al.
Published: (2025)

The Cylindrical Representation Hypothesis for Language Model Steering
by: Gao, Lang, et al.
Published: (2026)

SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models
by: Xu, Zixiang, et al.
Published: (2025)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
by: Liang, Jianxin, et al.
Published: (2025)

FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
by: Yin, Zhihan, et al.
Published: (2026)

MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
by: Wang, Yueqian, et al.
Published: (2025)

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
by: Yuan, Danlong, et al.
Published: (2026)

ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services
by: Ji, Fengxian, et al.
Published: (2026)

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
by: Song, Zirui, et al.
Published: (2025)

Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench
by: Huang, Jen-tse, et al.
Published: (2023)

Evaluating and Mitigating Bias in AI-Based Medical Text Generation
by: Chen, Xiuying, et al.
Published: (2025)

ReMamba: Equip Mamba with Effective Long-Sequence Modeling
by: Yuan, Danlong, et al.
Published: (2024)

Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
by: Liang, Jianxin, et al.
Published: (2025)

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
by: Wang, Yueqian, et al.
Published: (2024)

Content-based Controls For Music Large Language Modeling
by: Lin, Liwei, et al.
Published: (2023)

De-Anonymization at Scale via Tournament-Style Attribution
by: Zhang, Lirui, et al.
Published: (2026)

How Do They Feel? Processing Others’ Emotions in Second Language Discourse
by: Andrea González‐García Aldariz, et al.
Published: (2025)

Function Alignment: A New Theory of Mind and Intelligence, Part I: Foundations
by: Xia, Gus G.
Published: (2025)

Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
by: Xia, Haiying, et al.
Published: (2025)

Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMs
by: Song, Changhao, et al.
Published: (2025)

Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controls
by: Lin, Liwei, et al.
Published: (2024)

EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation
by: Izzati, Fathinah, et al.
Published: (2025)

The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents
by: Liu, Yuhan, et al.
Published: (2024)

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
by: Cheng, Xin, et al.
Published: (2024)

Shorten After You're Right: Lazy Length Penalties for Reasoning RL
by: Yuan, Danlong, et al.
Published: (2025)

PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection
by: Zhao, Rui, et al.
Published: (2025)

Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models
by: Xu, Zixiang, et al.
Published: (2025)

Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation
by: Liang, Yuxin, et al.
Published: (2024)