Cover Image

Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Wen, Song, Feifan, Li, Wei, Peng, Guangyue, Wei, Shaohang, Wang, Houfeng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
by: Luo, Wen, et al.
Published: (2026)

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
by: Song, Feifan, et al.
Published: (2025)

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction
by: Li, Wei, et al.
Published: (2025)

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
by: Luo, Wen, et al.
Published: (2026)

TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
by: Wei, Shaohang, et al.
Published: (2025)

REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
by: Chang, Haw-Shiuan, et al.
Published: (2024)

HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation
by: Luo, Wen, et al.
Published: (2024)

Mitigating Overthinking through Reasoning Shaping
by: Song, Feifan, et al.
Published: (2025)

Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
by: Arias, Esteban Garces, et al.
Published: (2024)

Improving Open-Ended Text Generation via Adaptive Decoding
by: Zhu, Wenhong, et al.
Published: (2024)

FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
by: Li, Wei, et al.
Published: (2025)

Detection-Correction Structure via General Language Model for Grammatical Error Correction
by: Li, Wei, et al.
Published: (2024)

Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
by: Peng, Guangyue, et al.
Published: (2026)

Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation
by: Arias, Esteban Garces, et al.
Published: (2024)

SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation
by: Xu, Ziyao, et al.
Published: (2024)

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
by: Song, Feifan, et al.
Published: (2024)

GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
by: Ding, Yuanhao, et al.
Published: (2025)

ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization
by: Song, Feifan, et al.
Published: (2024)

Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
by: Zhang, Yue, et al.
Published: (2023)

A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
by: Yang, Chenxu, et al.
Published: (2024)

Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation
by: Samarinas, Chris, et al.
Published: (2025)

The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention
by: Wan, Yixin, et al.
Published: (2024)

OpenEP: Open-Ended Future Event Prediction
by: Guan, Yong, et al.
Published: (2024)

Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification
by: Wang, Zihan, et al.
Published: (2024)

CiteCheck: Towards Accurate Citation Faithfulness Detection
by: Xu, Ziyao, et al.
Published: (2025)

Reverse-Engineered Reasoning for Open-Ended Generation
by: Wang, Haozhe, et al.
Published: (2025)

Self-Consistent Decoding for More Factual Open Responses
by: Malon, Christopher, et al.
Published: (2024)

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
by: Samvelyan, Mikayel, et al.
Published: (2024)

Preference Ranking Optimization for Human Alignment
by: Song, Feifan, et al.
Published: (2023)

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
by: Zhou, Yuxuan, et al.
Published: (2024)

Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
by: Arias, Esteban Garces, et al.
Published: (2024)

Open Systems Sing a Siren Song.
by: Webb, Terry D.
Published: (1987)

OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation
by: Lage, Lucas Fonseca, et al.
Published: (2025)

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
by: Carlsson, Fredrik, et al.
Published: (2024)

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
by: Das, Souvik, et al.
Published: (2024)

The Siren Song of Everest
by: Breashers, David F
Published: (1997)

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

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
by: Ye, Zhiling, et al.
Published: (2025)

P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis
by: Song, Feifan, et al.
Published: (2025)

A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds
by: Cui, Christopher Z., et al.
Published: (2024)