Imagen de Portada

The Straight and Narrow: Do LLMs Possess an Internal Moral Path?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hu, Luoming, Zeng, Jingjie, Yang, Liang, Lin, Hongfei
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Do Large Language Models Possess Sensitive to Sentiment?
por: Liu, Yang, et al.
Publicado: (2024)

STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection
por: Bai, Zewen, et al.
Publicado: (2025)

Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs
por: Huang, Jen-tse, et al.
Publicado: (2026)

Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?
por: Kadali, Sri Durga Sai Sowmya, et al.
Publicado: (2025)

Acquisition of Recursive Possessives and Recursive Locatives in Mandarin
por: Fu, Chenxi, et al.
Publicado: (2024)

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
por: Zeng, Zhiyuan, et al.
Publicado: (2025)

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
por: Yao, Yang, et al.
Publicado: (2025)

InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States
por: Beigi, Mohammad, et al.
Publicado: (2024)

Commonality and Individuality! Integrating Humor Commonality with Speaker Individuality for Humor Recognition
por: Zhu, Haohao, et al.
Publicado: (2025)

Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness
por: Cheang, Chi Seng, et al.
Publicado: (2025)

Common 7B Language Models Already Possess Strong Math Capabilities
por: Li, Chen, et al.
Publicado: (2024)

Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
por: Zhou, Jingyan, et al.
Publicado: (2023)

An ERP Study of Recursive Possessive Parsing in ASD Children and Its Cognitive Neuro Mechanisms
por: Chenxi, Fu, et al.
Publicado: (2026)

Integrating Multi-view Analysis: Multi-view Mixture-of-Expert for Textual Personality Detection
por: Zhu, Haohao, et al.
Publicado: (2024)

Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks
por: Bai, Zewen, et al.
Publicado: (2025)

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs
por: Yang, Zhipeng, et al.
Publicado: (2025)

MoralBench: Moral Evaluation of LLMs
por: Ji, Jianchao, et al.
Publicado: (2024)

Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm
por: Babarczy, Anna, et al.
Publicado: (2026)

Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG
por: Bang, Jihwan, et al.
Publicado: (2025)

Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations
por: Wang, Haoran, et al.
Publicado: (2026)

Children's Acquisition of Tail-recursion Sequences: A Review of Locative Recursion and Possessive Recursion as Examples
por: Wang, Xiaoyi, et al.
Publicado: (2024)

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
por: Zhao, Siyan, et al.
Publicado: (2025)

Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
por: Liu, Guangliang, et al.
Publicado: (2024)

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
por: Bergsma, Shane, et al.
Publicado: (2025)

Probing the Lack of Stable Internal Beliefs in LLMs
por: Luo, Yifan, et al.
Publicado: (2026)

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement
por: Lu, Junyu, et al.
Publicado: (2025)

Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM Framework
por: Xiao, Kelaiti, et al.
Publicado: (2025)

Moral Mazes in the Era of LLMs
por: Nguyen, Dang, et al.
Publicado: (2026)

AI Research Agents Narrow Scientific Exploration
por: Tang, Yixuan, et al.
Publicado: (2026)

IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models
por: Wang, Qiyao, et al.
Publicado: (2024)

HearSay Benchmark: Do Audio LLMs Leak What They Hear?
por: Wang, Jin, et al.
Publicado: (2026)

How Well Do LLMs Identify Cultural Unity in Diversity?
por: Li, Jialin, et al.
Publicado: (2024)

APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding
por: Liu, Mingdao, et al.
Publicado: (2024)

RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMs
por: Wang, Zhijun, et al.
Publicado: (2026)

Do Emotions Influence Moral Judgment in Large Language Models?
por: Saim, Mohammad, et al.
Publicado: (2026)

Do Large Language Models Understand Morality Across Cultures?
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Targeted Distillation for Sentiment Analysis
por: Zhang, Yice, et al.
Publicado: (2025)

Hallucination Detection with the Internal Layers of LLMs
por: Preiß, Martin
Publicado: (2025)

Seeing Straight: Document Orientation Detection for Efficient OCR
por: Goswami, Suranjan, et al.
Publicado: (2025)

Evaluating Gender Bias of LLMs in Making Morality Judgements
por: Bajaj, Divij, et al.
Publicado: (2024)