Cover Image

DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Yunzhen, Takase, Yusuke, Ishibashi, Yoichi, Shimodaira, Hidetoshi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Knowledge Sanitization of Large Language Models
by: Ishibashi, Yoichi, et al.
Published: (2023)

Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel
by: Yamagiwa, Hiroaki, et al.
Published: (2026)

Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors
by: Takase, Yusuke, et al.
Published: (2026)

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings
by: Yamagiwa, Hiroaki, et al.
Published: (2024)

Shimo Lab at "Discharge Me!": Discharge Summarization by Prompt-Driven Concatenation of Electronic Health Record Sections
by: He, Yunzhen, et al.
Published: (2024)

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

Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning
by: Ishibashi, Yoichi, et al.
Published: (2025)

Mapping 1,000+ Language Models via the Log-Likelihood Vector
by: Oyama, Momose, et al.
Published: (2025)

Zipfian Whitening
by: Yokoi, Sho, et al.
Published: (2024)

DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulation
by: Lee, Taeyeop, et al.
Published: (2025)

Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings
by: Kishino, Ryo, et al.
Published: (2025)

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

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
by: Chuang, Yung-Sung, et al.
Published: (2023)

Integrative Decoding: Improve Factuality via Implicit Self-consistency
by: Cheng, Yi, et al.
Published: (2024)

Subspace Representations for Soft Set Operations and Sentence Similarities
by: Ishibashi, Yoichi, et al.
Published: (2022)

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
by: Ishibashi, Yoichi, et al.
Published: (2024)

Conformal Language Model Reasoning with Coherent Factuality
by: Rubin-Toles, Maxon, et al.
Published: (2025)

Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models
by: Rubashevskii, Aleksandr, et al.
Published: (2026)

Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
by: Chang, Yurui, et al.
Published: (2025)

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
by: Yang, Junxiao, et al.
Published: (2025)

3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding
by: Zhu, Yihua, et al.
Published: (2023)

Norm of Mean Contextualized Embeddings Determines their Variance
by: Yamagiwa, Hiroaki, et al.
Published: (2024)

Improving Prediction Accuracy of Semantic Segmentation Methods Using Convolutional Autoencoder Based Pre-processing Layers
by: Shimodaira, Hisashi
Published: (2024)

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
by: Phan, Phuc, et al.
Published: (2024)

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

Logit Reweighting for Topic-Focused Summarization
by: Braun, Joschka, et al.
Published: (2025)

Less is More for Improving Automatic Evaluation of Factual Consistency
by: Wang, Tong, et al.
Published: (2024)

Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
by: Zhu, Yihua, et al.
Published: (2024)

$π^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models
by: Do, Quyet V., et al.
Published: (2026)

Social Genome: Grounded Social Reasoning Abilities of Multimodal Models
by: Mathur, Leena, et al.
Published: (2025)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
by: Ren, Liliang, et al.
Published: (2025)

LoCa: Logit Calibration for Knowledge Distillation
by: Yang, Runming, et al.
Published: (2024)

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

Scaling Speculative Decoding with Lookahead Reasoning
by: Fu, Yichao, et al.
Published: (2025)

Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
by: Hashimoto, Wataru, et al.
Published: (2025)

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning
by: Kachuee, Mohammad, et al.
Published: (2025)

Understanding Finetuning for Factual Knowledge Extraction
by: Ghosal, Gaurav, et al.
Published: (2024)

mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans
by: Sakai, Yusuke, et al.
Published: (2024)

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

On the Reasoning Abilities of Masked Diffusion Language Models
by: Svete, Anej, et al.
Published: (2025)