Cover Image

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Mingyu Derek, Ding, Yanna, Huang, Zijie, Gao, Jianxi, Sun, Yizhou, Wang, Wei
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation
by: Ding, Yanna, et al.
Published: (2024)

Predicting Time Series of Networked Dynamical Systems without Knowing Topology
by: Ding, Yanna, et al.
Published: (2024)

MIRAI: Evaluating LLM Agents for Event Forecasting
by: Ye, Chenchen, et al.
Published: (2024)

Large Language Model for Patent Concept Generation
by: Ren, Runtao, et al.
Published: (2024)

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
by: Choi, Hyeong Kyu, et al.
Published: (2026)

Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning
by: Ren, Runtao, et al.
Published: (2025)

Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis
by: Bhandari, Kushal Raj, et al.
Published: (2024)

Learning Generative Selection for Best-of-N
by: Toshniwal, Shubham, et al.
Published: (2026)

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
by: Hong, Fenglu, et al.
Published: (2025)

Enhancing Retrieval-Augmented Generation: A Study of Best Practices
by: Li, Siran, et al.
Published: (2025)

LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation
by: Meng, Fanjin, et al.
Published: (2026)

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
by: Ma, Mingyu Derek, et al.
Published: (2023)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
by: Huang, Kaixuan, et al.
Published: (2024)

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
by: Wang, Yiming, et al.
Published: (2025)

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

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
by: Li, Jin, et al.
Published: (2025)

RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish
by: Köse, Süha Kağan, et al.
Published: (2026)

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
by: Li, Yan, et al.
Published: (2025)

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
by: He, Jiashu, et al.
Published: (2024)

One2set + Large Language Model: Best Partners for Keyphrase Generation
by: Shao, Liangying, et al.
Published: (2024)

What is the Best Way for ChatGPT to Translate Poetry?
by: Wang, Shanshan, et al.
Published: (2024)

ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs
by: Chen, Keyu, et al.
Published: (2025)

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

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

Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
by: Chen, Zhijun, et al.
Published: (2025)

Unraveling the cognitive patterns of Large Language Models through module communities
by: Bhandari, Kushal Raj, et al.
Published: (2025)

Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework
by: Han, William, et al.
Published: (2025)

Pipelined Decoder for Efficient Context-Aware Text Generation
by: Huang, Zixian, et al.
Published: (2025)

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

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

Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models
by: Wei, Sheng-Lun, et al.
Published: (2024)

Reflection-Window Decoding: Text Generation with Selective Refinement
by: Tang, Zeyu, et al.
Published: (2025)

dInfer: An Efficient Inference Framework for Diffusion Language Models
by: Ma, Yuxin, et al.
Published: (2025)

Reinforced Context Order Recovery for Adaptive Reasoning and Planning
by: Ma, Long, et al.
Published: (2025)

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization
by: Zhang, Junlei, et al.
Published: (2025)

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection
by: Hu, Zhengyu, et al.
Published: (2026)

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

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
by: Zhang, Yunxiang, et al.
Published: (2025)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
by: Zhang, Kexun, et al.
Published: (2023)

Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection
by: He, Hongyi, et al.
Published: (2025)