Cover Image

Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Guangliang, Mao, Haitao, Tang, Jiliang, Johnson, Kristen Marie
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
by: Liu, Guangliang, et al.
Published: (2024)

A Survey to Recent Progress Towards Understanding In-Context Learning
by: Mao, Haitao, et al.
Published: (2024)

On the Convergence of Moral Self-Correction in Large Language Models
by: Liu, Guangliang, et al.
Published: (2025)

Discourse Heuristics For Paradoxically Moral Self-Correction
by: Liu, Guangliang, et al.
Published: (2025)

Self-correction is Not An Innate Capability in Language Models
by: Liu, Guangliang, et al.
Published: (2024)

Smaller Large Language Models Can Do Moral Self-Correction
by: Liu, Guangliang, et al.
Published: (2024)

Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
by: Liu, Guangliang, et al.
Published: (2025)

Learning to Diagnose and Correct Errors: Towards Moral Sensitivity Acquisition in Large Language Models
by: Chen, Bocheng, et al.
Published: (2026)

Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes
by: Liu, Guangliang, et al.
Published: (2025)

Pragmatic Inference for Moral Reasoning Acquisition: Generalization via Metapragmatic Links
by: Liu, Guangliang, et al.
Published: (2025)

Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
by: Liu, Guangliang, et al.
Published: (2024)

Revisiting the Superficial Alignment Hypothesis
by: Raghavendra, Mohit, et al.
Published: (2024)

Superficial Safety Alignment Hypothesis
by: Li, Jianwei, et al.
Published: (2024)

Superficial Self-Improved Reasoners Benefit from Model Merging
by: Yuan, Xiangchi, et al.
Published: (2025)

A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models
by: Braun, Marc, et al.
Published: (2024)

Label-free Node Classification on Graphs with Large Language Models (LLMS)
by: Chen, Zhikai, et al.
Published: (2023)

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
by: Xie, Jiakuan, et al.
Published: (2025)

Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems
by: So, Namyoung, et al.
Published: (2026)

The Straight and Narrow: Do LLMs Possess an Internal Moral Path?
by: Hu, Luoming, et al.
Published: (2026)

De-biased Multimodal Electrocardiogram Analysis
by: Li, Haitao, et al.
Published: (2024)

Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
by: Lin, Yuping, et al.
Published: (2024)

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment
by: Bhan, Milan, et al.
Published: (2025)

Understanding the Dark Side of LLMs' Intrinsic Self-Correction
by: Zhang, Qingjie, et al.
Published: (2024)

Automate Knowledge Concept Tagging on Math Questions with LLMs
by: Li, Hang, et al.
Published: (2024)

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
by: Han, Haoyu, et al.
Published: (2025)

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework
by: Huo, Yifu, et al.
Published: (2025)

Self-Debias: Self-correcting for Debiasing Large Language Models
by: Feng, Xuan, et al.
Published: (2026)

WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model
by: Fang, Tianqing, et al.
Published: (2025)

The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents
by: Chen, Chen, et al.
Published: (2026)

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
by: Xu, Zhu, et al.
Published: (2024)

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
by: Li, Yansi, et al.
Published: (2025)

Understanding Aha Moments: from External Observations to Internal Mechanisms
by: Yang, Shu, et al.
Published: (2025)

WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
by: Zhang, Zhisong, et al.
Published: (2025)

Extracting and Understanding the Superficial Knowledge in Alignment
by: Chen, Runjin, et al.
Published: (2025)

Confidence-Weighted Token Set Cover for Early Hypothesis Pruning in Self-Consistency
by: Sultan, Md Arafat, et al.
Published: (2025)

Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation
by: Chu, Yucheng, et al.
Published: (2025)

Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models
by: Parihar, Shweta, et al.
Published: (2026)

Self-Explaining Hate Speech Detection with Moral Rationales
by: Vargas, Francielle, et al.
Published: (2026)

Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
by: Li, Hang, et al.
Published: (2025)

Knowledge Tagging System on Math Questions via LLMs with Flexible Demonstration Retriever
by: Li, Hang, et al.
Published: (2024)