No article text was recorded for this version.
reversal curse
Version 1 of 1145 papers234 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Reverse Training to Nurse the Reversal Curse
- Blog: The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
- Blog: The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs
- Blog: Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
- Blog: Physics of Language Models: Part 3.2, Knowledge Manipulation
- Blog: Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms
- Blog: Beyond the Black Box: Theory and Mechanism of Large Language Models
- Blog: Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
- Blog: Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts
- Blog: Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
- Blog: Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge
- Blog: The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs
- Blog: Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
- Blog: Limited Out-of-Context Knowledge Reasoning in Large Language Models
- Blog: On the generalization of language models from in-context learning and finetuning: a controlled study
- Blog: Understanding the Reversal Curse Mitigation in Masked Diffusion Models through Attention and Training Dynamics
- Blog: Enabling LLM Knowledge Analysis via Extensive Materialization
- Blog: Physics of Language Models: Part 3.2, Knowledge Manipulation
- Blog: Can Language Models Act as Knowledge Bases at Scale?
- Blog: Reverse Modeling in Large Language Models
- Blog: Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
- Blog: Locating and Editing Factual Knowledge in GPT
- Blog: Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
- Blog: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
- Blog: Large Language Models are Limited in Out-of-Context Knowledge Reasoning
- Blog: Chiral Symmetry Breaking in Transformers: A Group-Equivariant Framework for Addressing the Reversal Curse via Adjoint Manifold Mappings
- Blog: Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs
- Blog: Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
- Blog: Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion
- Blog: Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse
- Blog: Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
- Blog: Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs
- Blog: Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity
- Blog: Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models' Understanding of Discourse Relations
- Blog: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
- Blog: Understanding the Logical Capabilities of Large Language Models via Out-of-Context Representation Learning
- Blog: The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
- Blog: Review of Hallucination Understanding in Large Language and Vision Models
- Blog: Closing the Data-Efficiency Gap Between Autoregressive and Masked Diffusion LLMs
- Blog: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
- Blog: Transitive Consistency Constrained Learning for Entity-to-Entity Stance Detection
- Blog: Learning Bidirectional Morphological Inflection like Humans
- Blog: THE ILLUSION OF LATENT GENERALIZATION: BI- DIRECTIONALITY AND THE REVERSAL CURSE
- Blog: ROME: Memorization Insights from Text, Probability and Hidden State in Large Language Models
- Blog: An Analysis and Mitigation of the Reversal Curse
- Blog: Large Language Diffusion Models
- Blog: Are Pretrained Language Models Symbolic Reasoners over Knowledge?
- Blog: Scaling Laws for Fact Memorization of Large Language Models
- Blog: Causality for Large Language Models
- Blog: ROME: Memorization Insights from Text, Logits and Representation
- Blog: Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal
- Blog: Reverse Training to Nurse the Reversal Curse
- Blog: Learning Directional Sentence-Pair Embedding for Natural Language Reasoning (Student Abstract)
- Blog: Make Your LLM Fully Utilize the Context
- Blog: DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
- Blog: Untying the Reversal Curse via Bidirectional Language Model Editing
- Blog: Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
- Blog: What if We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks
- Blog: GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding
- Blog: GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding
Showing 60 of 145 papers.
History & citation
Current · Permanent link
- The Reversal Curse in Large Language Models merged into this direction (100% overlap)
- Bidirectional Logical Generalization in Large Language Models merged into this direction (90% overlap)
- Directional Asymmetry in Autoregressive Language Models merged into this direction (70% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_reversal_curse_0bdaa52d,
title = {reversal curse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reversal-curse/rdr_0bdaa52d7b144ef6b6a5fe50d17215cb},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_reversal_curse_0bdaa52d_v1,
title = {reversal curse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reversal-curse/rdr_0bdaa52d7b144ef6b6a5fe50d17215cb/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}