Cover Image

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jin, Wang, Zhebo, Lu, Tianliang, Li, Mohan, Xing, Wenpeng, Han, Meng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sequences of Logits Reveal the Low Rank Structure of Language Models
by: Golowich, Noah, et al.
Published: (2025)

Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
by: Emadi, Seyed Morteza
Published: (2026)

On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
by: Fan, Chenghao, et al.
Published: (2024)

Logits are All We Need to Adapt Closed Models
by: Hiranandani, Gaurush, et al.
Published: (2025)

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access
by: Su, Jiayuan, et al.
Published: (2024)

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection
by: Ma, Mingyu Derek, et al.
Published: (2025)

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
by: Huang, Chengsong, et al.
Published: (2024)

Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
by: Ding, Yuanhao, et al.
Published: (2026)

ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
by: Wang, Zhebo, et al.
Published: (2026)

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
by: Zhang, Jianyi, et al.
Published: (2024)

Logit Dynamics in Softmax Policy Gradient Methods
by: Li, Yingru
Published: (2025)

Provably Learning from Modern Language Models via Low Logit Rank
by: Golowich, Noah, et al.
Published: (2025)

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

Sharp Spectral Thresholds for Logit Fixed Points
by: Wang, Tongxi
Published: (2026)

ROME: Memorization Insights from Text, Logits and Representation
by: Li, Bo, et al.
Published: (2024)

Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
by: Xu, Zhenhua, et al.
Published: (2024)

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

Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs
by: Anshumann, et al.
Published: (2025)

LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
by: Yu, Zhe, et al.
Published: (2026)

Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstruction
by: Lu, Shengyao, et al.
Published: (2025)

Formalising the Logit Shift Induced by LoRA: A Technical Note
by: Shi, Xiang, et al.
Published: (2026)

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

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
by: Li, Yuxi, et al.
Published: (2024)

Logits of API-Protected LLMs Leak Proprietary Information
by: Finlayson, Matthew, et al.
Published: (2024)

Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
by: Ma, Jing, et al.
Published: (2022)

Steering Language Models Before They Speak: Logit-Level Interventions
by: An, Hyeseon, et al.
Published: (2026)

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
by: Shivagunde, Namrata, et al.
Published: (2026)

RKadiyala at SemEval-2024 Task 8: Black-Box Word-Level Text Boundary Detection in Partially Machine Generated Texts
by: Kadiyala, Ram Mohan Rao
Published: (2024)

GoRA: Gradient-driven Adaptive Low Rank Adaptation
by: He, Haonan, et al.
Published: (2025)

SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments
by: Yang, Jiarong, et al.
Published: (2024)

From Projection to Prediction: Beyond Logits for Scalable Language Models
by: Dong, Jianbing, et al.
Published: (2025)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
by: Lin, Shi, et al.
Published: (2024)

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

Ensembles of Low-Rank Expert Adapters
by: Li, Yinghao, et al.
Published: (2025)

AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models
by: Liu, Zeyu, et al.
Published: (2024)

Text2Data: Low-Resource Data Generation with Textual Control
by: Wang, Shiyu, et al.
Published: (2024)

TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
by: Yang, Bohan, et al.
Published: (2026)

Logit Scaling for Out-of-Distribution Detection
by: Djurisic, Andrija, et al.
Published: (2024)

Direct-Inverse Prompting: Analyzing LLMs' Discriminative Capacity in Self-Improving Generation
by: Ahn, Jihyun Janice, et al.
Published: (2024)

Understanding Dynamic Compute Allocation in Recurrent Transformers
by: Moosa, Ibraheem Muhammad, et al.
Published: (2026)