Image de couverture de livre

LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Wang, Zhenyu
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DistillLens: Symmetric Knowledge Distillation Through Logit Lens
par: Dhakal, Manish, et autres
Publié: (2026)

Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
par: Phukan, Anirudh, et autres
Publié: (2024)

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits
par: Shao, Jintian, et autres
Publié: (2025)

DALD: Improving Logits-based Detector without Logits from Black-box LLMs
par: Zeng, Cong, et autres
Publié: (2024)

LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
par: He, Zirui, et autres
Publié: (2025)

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access
par: Su, Jiayuan, et autres
Publié: (2024)

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
par: Dong, Yijiang River, et autres
Publié: (2024)

Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs
par: Luo, Yiyang, et autres
Publié: (2024)

LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation
par: Chen, Jizheng, et autres
Publié: (2026)

Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
par: Geng, Saibo, et autres
Publié: (2024)

Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models
par: Shim, Jay, et autres
Publié: (2024)

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
par: Boizard, Nicolas, et autres
Publié: (2024)

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
par: Li, Jin, et autres
Publié: (2025)

Steering Language Models Before They Speak: Logit-Level Interventions
par: An, Hyeseon, et autres
Publié: (2026)

BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation
par: Li, Minchong, et autres
Publié: (2024)

Strategic Deflection: Defending LLMs from Logit Manipulation
par: Rachidy, Yassine, et autres
Publié: (2025)

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
par: Zhang, Jianyi, et autres
Publié: (2024)

Limits of n-gram Style Control for LLMs via Logit-Space Injection
par: Ahmed, Sami-ul
Publié: (2026)

Lens: Rethinking Multilingual Enhancement for Large Language Models
par: Zhao, Weixiang, et autres
Publié: (2024)

A Group Fairness Lens for Large Language Models
par: Bi, Guanqun, et autres
Publié: (2023)

Sequences of Logits Reveal the Low Rank Structure of Language Models
par: Golowich, Noah, et autres
Publié: (2025)

Logit Reweighting for Topic-Focused Summarization
par: Braun, Joschka, et autres
Publié: (2025)

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
par: Li, Songze, et autres
Publié: (2025)

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
par: Feng, Yingchaojie, et autres
Publié: (2024)

Understanding GUI Agent Localization Biases through Logit Sharpness
par: Tao, Xingjian, et autres
Publié: (2025)

Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs
par: Anshumann, et autres
Publié: (2025)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
par: Zhang, Yunxiang, et autres
Publié: (2025)

First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
par: Ha, Jiwoo, et autres
Publié: (2026)

LoCa: Logit Calibration for Knowledge Distillation
par: Yang, Runming, et autres
Publié: (2024)

Stabilizing Policy Optimization via Logits Convexity
par: Chen, Hongzhan, et autres
Publié: (2026)

Logits are All We Need to Adapt Closed Models
par: Hiranandani, Gaurush, et autres
Publié: (2025)

Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
par: Wang, Haonan, et autres
Publié: (2025)

Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior
par: Gong, Yue, et autres
Publié: (2025)

Logits of API-Protected LLMs Leak Proprietary Information
par: Finlayson, Matthew, et autres
Publié: (2024)

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
par: Wang, Yuanyi, et autres
Publié: (2025)

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
par: Ma, Ziyang, et autres
Publié: (2025)

Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion
par: Zhang, Chen, et autres
Publié: (2026)

Transferring Extreme Subword Style Using Ngram Model-Based Logit Scaling
par: Messner, Craig, et autres
Publié: (2025)

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)
par: Wang, Peidong
Publié: (2026)

StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
par: Sakajo, Haruki, et autres
Publié: (2026)