Token-Level Uncertainty

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

17 new papers

A weekly snapshot of new work published in Token-Level Uncertainty.

Period ending 2026-09-14

9 new papers

A weekly snapshot of new work published in Token-Level Uncertainty.

Period ending 2026-09-07

14 new papers

A weekly snapshot of new work published in Token-Level Uncertainty.

Inside this field

Focused directions

Focused topic

Token-Level Uncertainty

Within Token-Level Uncertainty

171 papersExplore

Focused topic

Tokenization

Within Token-Level Uncertainty

139 papersExplore

Focused topic

Latent Reasoning Tokens

Within Token-Level Uncertainty

55 papersExplore

Focused topic

Discrete Tokens

Within Token-Level Uncertainty

49 papersExplore

Focused topic

Token Communications

Within Token-Level Uncertainty

39 papersExplore

Focused topic

Byte-Pair Encoding

Within Token-Level Uncertainty

27 papersExplore

Focused topic

Subword Tokenization

Within Token-Level Uncertainty

27 papersExplore

473 papers

Latest in Token-Level Uncertainty

Browse all topics →

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
Jun 4, 2026Gizem Yüce, Giorgos Nikolaou, Nicolas FlammarionLarge Language Model Unlearning Autoregressive Language Models
RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
Jun 4, 2026Yang Liu, ZhaoKai Luo, HuaYi Jin +5Key-Value Cache Large Language Model Serving
LLM-Conditioned Synthesis of Pathological Gaits via Structured Gait-Language Representations
Jun 4, 2026Mritula Chandrasekaran, Sanket Kachole, Jarek Francik +1Single-Subject Gait Dataset Gait Recognition
NAVIRA: Decoupled Stochastic Remasking for Masked Diffusion Language Models
Jun 4, 2026Andrey Fomenko, Maksim Kryzhanovskiy, Svetlana Glazyrina +1Masked Diffusion Language Models Diffusion Language Models
FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG
Jun 4, 2026Zhe Yu, Wenpeng Xing, Tiancheng Zhao +3Contrastive Decoding Retrieval-Augmented Generation Systems
Balancing Image Compression and Generation with Bootstrapped Tokenization
Jun 4, 2026Haozhe Chi, Jinghan Li, Hao Jiang +4Tokenization Self-Supervised Reconstruction Method
GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
Jun 3, 2026Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Kumar Gyawali +2Tabular Foundation Models Tabpfn
Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
Jun 3, 2026Kyungmin Park, Taesup KimInference-Time Defense Large Language Model Safety
LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
Jun 3, 2026Daria Ledneva, Denis KuznetsovGenomics Wireless Foundation Models
LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
Jun 3, 2026Yuanrui Wang, Xingxuan Zhang, Han Yu +7Tabular Foundation Models Tensor Programs
ChannelTok: Efficient Flexible-Length Vision Tokenization
Jun 3, 2026Sukriti Paul, Arpit Bansal, Tom GoldsteinVisual Tokens Tokenization
CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding
Jun 3, 2026Eugene Kwek, Feng Liu, Rui Zhang +1Neural Audio Codecs Audio Tokens
MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers
Jun 3, 2026Yanshun Zhao, Xiaoyu Peng, Jiamin Jiang +2Neural Partial Differential Equation Solvers Tokenization
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
Jun 2, 2026Johanne Medina, Tianyi Zhou, Keivin Isufaj +2Large Language Model Uncertainty Hidden States
When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models
Jun 2, 2026Ding Zhang, Runtao Zhou, Wenqing Zheng +3Graph Language Models Discrete Tokens
Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI
Jun 2, 2026Amjad Ibrahim, Yong LiDelegation Authorization
Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
Jun 2, 2026Ruipeng Zhang, Zhihao Li, C. L. Philip Chen +1Large Language Model Hallucination Large Vision Language Models
TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching
Jun 2, 2026Zhe Li, Jindong Tian, Hao Miao +3Multivariate Time Series Forecasting Temporal Dynamics
Large Byte Model: Teaching Language Models About Compiled Code
Jun 1, 2026Florian Störtz, Catalin-Andrei Stan, Alexandru Dinu +4Malware Detection Tokenization
EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
Jun 1, 2026Hui Li, Yangfan Gao, Junlin Shang +4Audio Tokens Tokenization
PortBERT: Navigating the Depths of Portuguese Language Models
Jun 1, 2026Raphael Scheible-Schmitt, Henry He, Armando B. MendesBert-Based Models Portuguese
Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning
Jun 1, 2026Ziyang Yao, Zeyu Zhu, YunCheng Jiang +2Autonomous Driving Visual Tokens
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
Jun 1, 2026Liu Qing, Ou Wu, Yi DuLarge Language Model Post-Training Token-Level Uncertainty
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
May 31, 2026Yuhang Zhou, Lizhu Zhang, Yifan Wu +5On-Policy Distillation Token-Level Uncertainty
Learning from Saturated Data: Signals Beyond Correctness for LLM Training
May 31, 2026Hanno Hiss, Jasper Dekoninck, Martin VechevLarge Language Model Judges Correctness
LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
May 31, 2026Mengmeng Ji, Ravi Shanker Raju, Jonathan Lingjie Li +1Efficient Long-Context Inference Context Length
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
May 31, 2026Yunhao Zhang, Ruiying Qi, Jiale Zheng +3Time Series Foundation Models Time Series
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
May 31, 2026Mingxi LiGenerative Super-Resolution Calibration-Free Low-Bit Vector Quantization
Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals
May 30, 2026Shenghao DingAudio Tokens Discrete Wavelet Transform
DeepLatent: Think with Images via Parallel Latent Visual Reasoning
May 30, 2026Dongchen Lu, Zhimo Li, Mao Shu +1Latent Visual Reasoning Large Vision Language Models
V-LynX: Token Interface Alignment for Video+X LLMs
May 30, 2026Jungin Park, Jiyoung Lee, Kwanghoon SohnVisual Tokens Modality-Specific Encoders
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
May 29, 2026Mungyeom Kim, Minkyeong Jeon, Honggyu An +104D Reconstruction Monocular Videos
Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
May 29, 2026Benedetta Muscato, Beiduo Chen, Gizem Gezici +2Hate Speech Explainability
UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception
May 29, 2026Yuhan Song, Linhao Zhang, Aiwei Liu +6Audio Tokens Tokenization
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
May 29, 2026Yi Liu, Hongji Zhang, Lei Chen +2Flexible Register Transfer Level Design Automation Register Transfer Level
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
May 29, 2026Luyuan Zhang, Siyuan Li, Zedong Wang +7Visual Tokens Tokenization
Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
May 29, 2026Yanjiang Liu, Jie Lou, Xinyan Guan +7On-Policy Distillation Teacher
Incremental BPE Tokenization
May 29, 2026Shenghu Jiang, Ruihao GongByte-Pair Encoding Tokenization
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
May 28, 2026Zhihao Wu, Gracia Gong, Qinglin Zhu +2Large Language Model Watermarks Watermarking
MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
May 28, 2026Kexin Chu, Yang Zhou, Wei ZhangLLM Inference Efficiency Token-Level Uncertainty
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
May 28, 2026Travis LelleBackdoor Attacks Language Model Evasion Attacks
Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation
May 28, 2026M. Ali Bayram, Banu Diri, Savaş YıldırımTokenization Multilingual
HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
May 28, 2026Bohan Li, Shi Lian, Hankun Wang +6Audio Tokens Tokenization
Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation
May 28, 2026Soumyadeep Jana, Sagar Nishad, Sanasam Ranbir SinghKey-Value Cache Compression Efficient Long-Context Inference
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
May 28, 2026Alexander Sternfeld, Andrei Kucharavy, Ljiljana DolamicVulnerable Code Vulnerability Detection & Repair
DLM-SWAI: Steering Diffusion Language Models Before They Unmask
May 28, 2026Hyeseon An, Yo-Sub HanDiffusion Language Models Activation Steering
Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion
May 28, 2026Yizhuo Lu, Changde Du, Qingyu Shi +5Brain-Computer Interface Multi--Task Learning
Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
May 28, 2026Rohan ShravanByte-Pair Encoding
BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base
May 28, 2026Rohan ShravanByte-Pair Encoding Context Compression
Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text
May 27, 2026Bushi Xiao, Sarvesh Soni, Daisy Zhe WangLarge Language Model Uncertainty Token-Level Uncertainty
Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection
May 27, 2026Zhixing Zuo, Huilin He, Jiasheng Wu +1Fraud Detection Deep Semantic Representations
Chinese Word Boundary Recovery through Character Alignment Projection
May 27, 2026Lusha Wang, Yuchen Li, Su Yuan +1Sharp Boundary Delineation Subword Tokenization
Patched-DeltaNet: Token-Level Event-Driven Memory for Linear-Time Anomaly Detection
May 27, 2026Tae-Gyun Lee, Junyoung Park, Kyu Won HanTime-Series Anomaly Detection Change-Point Detection
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
May 27, 2026Eric Onyame, Runtao Zhou, Kowshik Thopalli +2Adversarial Evaluation Chain-of-Thought Reasoning
Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration
May 26, 2026Hankyeol Kim, Pilsung KangLarge Language Model Uncertainty Token-Level Uncertainty
Bounded-Compute Multimodal Regression for Product-Rating Prediction
May 26, 2026William Leach, Ru He, Sizhuo Ma +4Multimodal Evaluation Multimodal Classification
Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment
May 26, 2026Bruce Changlong Xu, Lan WuTraining-Free Inference Framework LLM Post-Training Methods
Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation
May 26, 2026Joseph Hoche, David Brellmann, Gianni FranchiLarge Vision Language Models Large Language Model Uncertainty
Cultural Value Alignment Via Latent Activation Steering in Large Language Models
May 25, 2026Trung Duc Anh Dang, Sarah MasudLarge Language Model Alignment Cultural Knowledge
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
May 25, 2026Georgios Milis, Yubin Qin, Yihan Wu +1Watermarking Watermarks

Jun 4, 2026 · cs.LGJ/K move · Enter open · S save

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

Gizem Yüce, Giorgos Nikolaou, Nicolas Flammarion

Theory of Machine Learning Lab, EPFL

Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities. For autoregressive language models, not all tokens in a forget sample are equally relevant to forgetting. Existing approaches either ignore this heterogeneity or rely on auxiliary models, heuristics, or external annotations to estimate each token's relevance for forgetting. We instead characterize it through the interaction with the retain objective: a token is forget-specific to the extent that minimizing the forget loss on that token does not conflict with retain optimality. We formalize this perspective as a joint optimization problem over the model parameters and the token weights and show that, under a natural separation condition, the resulting objective recovers the oracle forget-specific token support. Motivated by this formulation, we introduce Alternating Token-Weighted Unlearning (ATWU), a lightweight framework that jointly learns token forget-specificity and model parameters during unlearning using a simple linear scorer over the hidden states, without external token level supervision. Across TOFU and RWKU, ATWU achieves state of the art forget-retain trade-offs, outperforming sample-level methods, probability-based token weighting heuristics, and auxiliary-model-based approaches. Moreover, the learned scores align substantially better with ground truth forget-specific spans, indicating that ATWU identifies semantically meaningful token level forgetting signals. Overall, our results suggest that retain conflict provides an effective criterion for identifying what language models should forget, enabling unsupervised learning of token level forget-specificity directly from model representations with minimal computational overhead.

Large Language Model Unlearning Autoregressive Language Models Token-Level Uncertainty

Open paper Ask about it PDF