Copertina

Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zixiao, Zhu, Zijian, Feng, Hanzhang, Zhou, Junlang, Qian, Kezhi, Mao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unveiling and Manipulating Prompt Influence in Large Language Models
di: Feng, Zijian, et al.
Pubblicazione: (2024)

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
di: Zhou, Hanzhang, et al.
Pubblicazione: (2024)

LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction
di: Zhou, Hanzhang, et al.
Pubblicazione: (2023)

Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction
di: Qian, Junlang, et al.
Pubblicazione: (2025)

FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation
di: Feng, Zijian, et al.
Pubblicazione: (2024)

Domain Lexical Knowledge-based Word Embedding Learning for Text Classification under Small Data
di: Zhu, Zixiao, et al.
Pubblicazione: (2025)

Fine-Grained Activation Steering: Steering Less, Achieving More
di: Feng, Zijian, et al.
Pubblicazione: (2026)

Rethinking Prompt Optimizers: From Prompt Merits to Optimization
di: Zhu, Zixiao, et al.
Pubblicazione: (2025)

On Support Samples of Next Word Prediction
di: Li, Yuqian, et al.
Pubblicazione: (2025)

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

Label Words as Local Task Vectors in In-Context Learning
di: Zheng, Bowen, et al.
Pubblicazione: (2024)

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

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
di: Wang, Siyuan, et al.
Pubblicazione: (2025)

LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
di: He, Zirui, et al.
Pubblicazione: (2025)

BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation
di: Li, Minchong, et al.
Pubblicazione: (2024)

Using Context to Improve Word Segmentation
di: Hu, Stephanie, et al.
Pubblicazione: (2025)

A Grounded Typology of Word Classes
di: Haley, Coleman, et al.
Pubblicazione: (2024)

CodeDelegator: Mitigating Context Pollution via Role Separation in Code-as-Action Agents
di: Fei, Tianxiang, et al.
Pubblicazione: (2026)

Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
di: Yigit, Gulsum, et al.
Pubblicazione: (2024)

Rapid Word Learning Through Meta In-Context Learning
di: Wang, Wentao, et al.
Pubblicazione: (2025)

Rewards as Labels: Revisiting RLVR from a Classification Perspective
di: Zhai, Zepeng, et al.
Pubblicazione: (2026)

Author-Specific Linguistic Patterns Unveiled: A Deep Learning Study on Word Class Distributions
di: Krauss, Patrick, et al.
Pubblicazione: (2025)

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits
di: Shao, Jintian, et al.
Pubblicazione: (2025)

LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models
di: Wang, Zhenyu
Pubblicazione: (2025)

GATEAU: Selecting Influential Samples for Long Context Alignment
di: Si, Shuzheng, et al.
Pubblicazione: (2024)

TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment
di: Li, Zheng, et al.
Pubblicazione: (2025)

Curriculum Demonstration Selection for In-Context Learning
di: Vu, Duc Anh, et al.
Pubblicazione: (2024)

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
di: Blau, Tsachi, et al.
Pubblicazione: (2024)

STAYKATE: Hybrid In-Context Example Selection Combining Representativeness Sampling and Retrieval-based Approach -- A Case Study on Science Domains
di: Zhu, Chencheng, et al.
Pubblicazione: (2024)

Stabilizing Policy Optimization via Logits Convexity
di: Chen, Hongzhan, et al.
Pubblicazione: (2026)

Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion
di: Zhang, Chen, et al.
Pubblicazione: (2026)

Restoring Pruned Large Language Models via Lost Component Compensation
di: Feng, Zijian, et al.
Pubblicazione: (2025)

LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation
di: Chen, Jizheng, et al.
Pubblicazione: (2026)

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
di: Tang, Yuwei, et al.
Pubblicazione: (2024)

CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge Conflicts
di: Ma, Xuhua, et al.
Pubblicazione: (2026)

Revisiting Demonstration Selection Strategies in In-Context Learning
di: Peng, Keqin, et al.
Pubblicazione: (2024)

Advancing the Arabic WordNet: Elevating Content Quality
di: Freihat, Abed Alhakim, et al.
Pubblicazione: (2024)

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents
di: Zhu, Ming, et al.
Pubblicazione: (2024)

Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models
di: Shim, Jay, et al.
Pubblicazione: (2024)

Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
di: Yu, Tian, et al.
Pubblicazione: (2024)