Intrinsic Test of Unlearning Using Parametric Knowledge Traces
Fuente:
arXiv
Saved in:
| Main Authors: | Hong, Yihuai, Yu, Lei, Yang, Haiqin, Ravfogel, Shauli, Geva, Mor |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
State over Tokens: Characterizing the Role of Reasoning Tokens
by: Levy, Mosh, et al.
Published: (2025)
by: Levy, Mosh, et al.
Published: (2025)
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
by: Shafran, Or, et al.
Published: (2026)
by: Shafran, Or, et al.
Published: (2026)
Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024)
by: Ravfogel, Shauli, et al.
Published: (2024)
From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
by: Ivgi, Maor, et al.
Published: (2024)
by: Ivgi, Maor, et al.
Published: (2024)
Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
by: Yona, Itay, et al.
Published: (2026)
by: Yona, Itay, et al.
Published: (2026)
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction
by: Hong, Yihuai, et al.
Published: (2025)
by: Hong, Yihuai, et al.
Published: (2025)
Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
by: Katz, Shahar, et al.
Published: (2024)
by: Katz, Shahar, et al.
Published: (2024)
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
by: Ghandeharioun, Asma, et al.
Published: (2024)
by: Ghandeharioun, Asma, et al.
Published: (2024)
Can LLMs Introspect? A Reality Check
by: Singh, Shashwat, et al.
Published: (2026)
by: Singh, Shashwat, et al.
Published: (2026)
Dissecting Fine-Tuning Unlearning in Large Language Models
by: Hong, Yihuai, et al.
Published: (2024)
by: Hong, Yihuai, et al.
Published: (2024)
Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
by: Parmar, Mihir, et al.
Published: (2022)
by: Parmar, Mihir, et al.
Published: (2022)
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
by: Tan, Yuqiao, et al.
Published: (2025)
by: Tan, Yuqiao, et al.
Published: (2025)
Latent Reasoning with Supervised Thinking States
by: Amos, Ido, et al.
Published: (2026)
by: Amos, Ido, et al.
Published: (2026)
Precise In-Parameter Concept Erasure in Large Language Models
by: Gur-Arieh, Yoav, et al.
Published: (2025)
by: Gur-Arieh, Yoav, et al.
Published: (2025)
Unlearning Traces the Influential Training Data of Language Models
by: Isonuma, Masaru, et al.
Published: (2024)
by: Isonuma, Masaru, et al.
Published: (2024)
CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept
by: Wu, YuXuan, et al.
Published: (2024)
by: Wu, YuXuan, et al.
Published: (2024)
Estimating Knowledge in Large Language Models Without Generating a Single Token
by: Gottesman, Daniela, et al.
Published: (2024)
by: Gottesman, Daniela, et al.
Published: (2024)
Log-linear Guardedness and its Implications
by: Ravfogel, Shauli, et al.
Published: (2022)
by: Ravfogel, Shauli, et al.
Published: (2022)
Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?
by: Yona, Gal, et al.
Published: (2024)
by: Yona, Gal, et al.
Published: (2024)
From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering
by: Li, Lei, et al.
Published: (2025)
by: Li, Lei, et al.
Published: (2025)
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
by: Lin, Yujie, et al.
Published: (2026)
by: Lin, Yujie, et al.
Published: (2026)
Learning and Unlearning of Fabricated Knowledge in Language Models
by: Sun, Chen, et al.
Published: (2024)
by: Sun, Chen, et al.
Published: (2024)
Safety Alignment via Constrained Knowledge Unlearning
by: Shi, Zesheng, et al.
Published: (2025)
by: Shi, Zesheng, et al.
Published: (2025)
When Can Transformers Count to n?
by: Yehudai, Gilad, et al.
Published: (2024)
by: Yehudai, Gilad, et al.
Published: (2024)
MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents
by: Wolfson, Tomer, et al.
Published: (2025)
by: Wolfson, Tomer, et al.
Published: (2025)
EasyECR: A Library for Easy Implementation and Evaluation of Event Coreference Resolution Models
by: Li, Yuncong, et al.
Published: (2024)
by: Li, Yuncong, et al.
Published: (2024)
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
by: Gekhman, Zorik, et al.
Published: (2026)
by: Gekhman, Zorik, et al.
Published: (2026)
MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
by: Li, Runze, et al.
Published: (2026)
by: Li, Runze, et al.
Published: (2026)
Explainable Few-shot Knowledge Tracing
by: Li, Haoxuan, et al.
Published: (2024)
by: Li, Haoxuan, et al.
Published: (2024)
IQ Test for LLMs: An Evaluation Framework for Uncovering Core Skills in LLMs
by: Maimon, Aviya, et al.
Published: (2025)
by: Maimon, Aviya, et al.
Published: (2025)
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
by: Ben-Zaken, Elad, et al.
Published: (2021)
by: Ben-Zaken, Elad, et al.
Published: (2021)
A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge
by: Song, Jongyoon, et al.
Published: (2025)
by: Song, Jongyoon, et al.
Published: (2025)
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
by: Kim, Minsung, et al.
Published: (2025)
by: Kim, Minsung, et al.
Published: (2025)
Geometric Factual Recall in Transformers
by: Ravfogel, Shauli, et al.
Published: (2026)
by: Ravfogel, Shauli, et al.
Published: (2026)
ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
by: Zeng, Ziqian, et al.
Published: (2023)
by: Zeng, Ziqian, et al.
Published: (2023)
Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
by: Vazhentsev, Artem, et al.
Published: (2026)
by: Vazhentsev, Artem, et al.
Published: (2026)
KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
by: Li, Rui, et al.
Published: (2025)
by: Li, Rui, et al.
Published: (2025)
Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation
by: Bhambri, Siddhant, et al.
Published: (2025)
by: Bhambri, Siddhant, et al.
Published: (2025)
Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
by: Nemkova, Apollinaire Poli, et al.
Published: (2025)
by: Nemkova, Apollinaire Poli, et al.
Published: (2025)
Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
by: Blum, Carter, et al.
Published: (2025)
by: Blum, Carter, et al.
Published: (2025)
Similar Items
-
State over Tokens: Characterizing the Role of Reasoning Tokens
by: Levy, Mosh, et al.
Published: (2025) -
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
by: Shafran, Or, et al.
Published: (2026) -
Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024) -
From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
by: Ivgi, Maor, et al.
Published: (2024) -
Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
by: Yona, Itay, et al.
Published: (2026)