Cover Image

From Logits to Latents: Contrastive Representation Shaping for LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Haoran, Khanna, Rajiv
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sharpness-Aware Machine Unlearning
by: Tang, Haoran, et al.
Published: (2025)

Why Some Models Resist Unlearning: A Linear Stability Perspective
by: Chang, Wei-Kai, et al.
Published: (2026)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
by: Zhong, Yisheng, et al.
Published: (2026)

Federated Contrastive Learning of Graph-Level Representations
by: Li, Xiang, et al.
Published: (2024)

Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
by: Chang, Wei-Kai, et al.
Published: (2025)

A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
by: Chang, Wei-Kai, et al.
Published: (2025)

Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
by: Lee, Hong kyu, et al.
Published: (2024)

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
by: Hu, Zizhao, et al.
Published: (2026)

Logit Distance Bounds Representational Similarity
by: Nielsen, Beatrix M. G., et al.
Published: (2026)

SAMOSA: Sharpness Aware Minimization for Open Set Active learning
by: Kim, Young In, et al.
Published: (2025)

Logit Distillation on Manifolds: Mapping by Learning
by: Yang, Yiru, et al.
Published: (2026)

Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
by: Liu, Xin, et al.
Published: (2025)

Machine Unlearning in Contrastive Learning
by: Wang, Zixin, et al.
Published: (2024)

The Space Complexity of Approximating Logistic Loss
by: Dexter, Gregory, et al.
Published: (2024)

Structure-Aware Spectral Sparsification via Uniform Edge Sampling
by: He, Kaiwen, et al.
Published: (2025)

An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations
by: Gao, Yichen, et al.
Published: (2026)

PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
by: Chen, Xiaoyi, et al.
Published: (2026)

Logits Poisoning Attack in Federated Distillation
by: Tang, Yuhan, et al.
Published: (2024)

Top-$nσ$: Not All Logits Are You Need
by: Tang, Chenxia, et al.
Published: (2024)

Guardrails in Logit Space: Safety Token Regularization for LLM Alignment
by: Bach, Thong, et al.
Published: (2026)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
by: Spohn, Philipp, et al.
Published: (2025)

LLM Unlearning with LLM Beliefs
by: Li, Kemou, et al.
Published: (2025)

Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration
by: Amin, Hasan, et al.
Published: (2026)

Structured Contrastive Learning for Interpretable Latent Representations
by: Shen, Zhengyang, et al.
Published: (2025)

Deconstructing Positional Information: From Attention Logits to Training Biases
by: Gu, Zihan, et al.
Published: (2025)

Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization
by: Amin, Hasan, et al.
Published: (2026)

Erase at the Core: Representation Unlearning for Machine Unlearning
by: Lee, Jaewon, et al.
Published: (2026)

Unlearning via Sparse Representations
by: Shah, Vedant, et al.
Published: (2023)

DALD: Improving Logits-based Detector without Logits from Black-box LLMs
by: Zeng, Cong, et al.
Published: (2024)

MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
by: Wang, Yihan, et al.
Published: (2024)

Representation Unlearning: Forgetting through Information Compression
by: Almudévar, Antonio, et al.
Published: (2026)

Gauss-Newton Unlearning for the LLM Era
by: McKinney, Lev, et al.
Published: (2026)

Logits-Based Finetuning
by: Li, Jingyao, et al.
Published: (2025)

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
by: Shan, Lianlei, et al.
Published: (2026)

Learning-Time Encoding Shapes Unlearning in LLMs
by: Wu, Ruihan, et al.
Published: (2025)

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
by: Doshi, Jai, et al.
Published: (2024)

ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation
by: Liu, Chenzhi, et al.
Published: (2025)

Adversarial Mixup Unlearning
by: Peng, Zhuoyi, et al.
Published: (2025)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
by: Wang, Bin, et al.
Published: (2026)

Node-level Contrastive Unlearning on Graph Neural Networks
by: Lee, Hong kyu, et al.
Published: (2025)