Cover Image

An Analysis and Mitigation of the Reversal Curse

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lv, Ang, Zhang, Kaiyi, Xie, Shufang, Tu, Quan, Chen, Yuhan, Wen, Ji-Rong, Yan, Rui
Format:	Preprint
Published:	2023
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
by: Lv, Ang, et al.
Published: (2024)

Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
by: Guo, Qingyan, et al.
Published: (2024)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
by: Zhang, Kaiyi, et al.
Published: (2025)

The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
by: Kitouni, Ouail, et al.
Published: (2024)

Language Models "Grok" to Copy
by: Lv, Ang, et al.
Published: (2024)

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
by: Chen, Changyu, et al.
Published: (2024)

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
by: Ban, Hao, et al.
Published: (2025)

Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
by: Chen, Yuhan, et al.
Published: (2023)

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
by: Berglund, Lukas, et al.
Published: (2023)

HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
by: Chen, Yuhan, et al.
Published: (2024)

More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
by: Zhang, Xiaoqing, et al.
Published: (2025)

On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
by: Wang, Yiming, et al.
Published: (2026)

Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
by: Zhang, Kaiyi, et al.
Published: (2024)

Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models
by: Wu, Da, et al.
Published: (2023)

Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis
by: Kapl, Ferdinand, et al.
Published: (2025)

More Expressive Attention with Negative Weights
by: Lv, Ang, et al.
Published: (2024)

Autonomy-of-Experts Models
by: Lv, Ang, et al.
Published: (2025)

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
by: He, Shwai, et al.
Published: (2025)

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
by: Jeon, Moongyu, et al.
Published: (2026)

DeepCritic: Deliberate Critique with Large Language Models
by: Yang, Wenkai, et al.
Published: (2025)

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
by: Chen, Zhipeng, et al.
Published: (2026)

Understanding and Mitigating the Uncertainty in Zero-Shot Translation
by: Wang, Wenxuan, et al.
Published: (2022)

Reverse Training to Nurse the Reversal Curse
by: Golovneva, Olga, et al.
Published: (2024)

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
by: Dong, Guanting, et al.
Published: (2024)

SMART: Self-Aware Agent for Tool Overuse Mitigation
by: Qian, Cheng, et al.
Published: (2025)

Masked Diffusion Models as Energy Minimization
by: Chen, Sitong, et al.
Published: (2025)

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
by: Gerstgrasser, Matthias, et al.
Published: (2024)

Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning
by: Gong, Zhaoyan, et al.
Published: (2026)

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
by: Song, Xiaoshuai, et al.
Published: (2026)

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
by: Lai, Song, et al.
Published: (2025)

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2024)

Delving into Muon and Beyond: Deep Analysis and Extensions
by: Qi, Xianbiao, et al.
Published: (2026)

Towards Effective Code-Integrated Reasoning
by: Bai, Fei, et al.
Published: (2025)

Reverse Thinking Makes LLMs Stronger Reasoners
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
by: Wang, Shida, et al.
Published: (2023)

CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
by: Shim, Jung-Woo, et al.
Published: (2025)

Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models
by: Shim, Jung-Woo, et al.
Published: (2025)

Reverse-Engineering the Reader
by: Kiegeland, Samuel, et al.
Published: (2024)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
by: Chen, Lichang, et al.
Published: (2024)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)