Copertina

Collaborative decoding of critical tokens for boosting factuality of large language models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jin, Lifeng, Peng, Baolin, Song, Linfeng, Mi, Haitao, Tian, Ye, Yu, Dong
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

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
di: Tian, Ye, et al.
Pubblicazione: (2024)

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

SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
di: Yu, Dian, et al.
Pubblicazione: (2024)

Self-Consistency Boosts Calibration for Math Reasoning
di: Wang, Ante, et al.
Pubblicazione: (2024)

Fine-Grained Self-Endorsement Improves Factuality and Reasoning
di: Wang, Ante, et al.
Pubblicazione: (2024)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
di: Zhang, Xiaoying, et al.
Pubblicazione: (2024)

Inconsistent dialogue responses and how to recover from them
di: Zhang, Mian, et al.
Pubblicazione: (2024)

Long-form factuality in large language models
di: Wei, Jerry, et al.
Pubblicazione: (2024)

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
di: Wang, Xiyao, et al.
Pubblicazione: (2024)

A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
di: Li, Xiangci, et al.
Pubblicazione: (2024)

Measuring short-form factuality in large language models
di: Wei, Jason, et al.
Pubblicazione: (2024)

LiteSearch: Efficacious Tree Search for LLM
di: Wang, Ante, et al.
Pubblicazione: (2024)

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
di: Zhang, Yuheng, et al.
Pubblicazione: (2024)

Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
di: Zhang, Xiaoying, et al.
Pubblicazione: (2024)

Revisiting subword tokenization: A case study on affixal negation in large language models
di: Truong, Thinh Hung, et al.
Pubblicazione: (2024)

Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
di: Wang, Ante, et al.
Pubblicazione: (2025)

Teaching LLMs to Refine with Tools
di: Yu, Dian, et al.
Pubblicazione: (2024)

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
di: Yu, Dian, et al.
Pubblicazione: (2025)

Universal computation is intrinsic to language model decoding
di: Lewandowski, Alex, et al.
Pubblicazione: (2026)

Automata-based constraints for language model decoding
di: Koo, Terry, et al.
Pubblicazione: (2024)

A benchmark dataset for evaluating Syndrome Differentiation and Treatment in large language models
di: Li, Kunning, et al.
Pubblicazione: (2025)

Do language models plan ahead for future tokens?
di: Wu, Wilson, et al.
Pubblicazione: (2024)

Visualizing token importance for black-box language models
di: Rauba, Paulius, et al.
Pubblicazione: (2025)

IYKYK: Using language models to decode extremist cryptolects
di: de Kock, Christine, et al.
Pubblicazione: (2025)

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
di: Su, Yi, et al.
Pubblicazione: (2025)

CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
di: Liang, Zhenwen, et al.
Pubblicazione: (2025)

MLRIP: Pre-training a military language representation model with informative factual knowledge and professional knowledge base
di: Li, Hui, et al.
Pubblicazione: (2022)

Verified Critical Step Optimization for LLM Agents
di: Li, Mukai, et al.
Pubblicazione: (2026)

On the scaling relationship between cloze probabilities and language model next-token prediction
di: Jacobs, Cassandra L., et al.
Pubblicazione: (2026)

Comparative analysis of subword tokenization approaches for Indian languages
di: Das, Sudhansu Bala, et al.
Pubblicazione: (2025)

VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation
di: Song, Yixiao, et al.
Pubblicazione: (2024)

HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving
di: Li, Yang, et al.
Pubblicazione: (2024)

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
di: Li, Mukai, et al.
Pubblicazione: (2025)

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
di: Yao, Wenlin, et al.
Pubblicazione: (2024)

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
di: Zhang, Yuheng, et al.
Pubblicazione: (2025)

From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries
di: Wadhwa, Hitesh, et al.
Pubblicazione: (2024)

DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis
di: Georgiou, Efthymios, et al.
Pubblicazione: (2025)

Streamlining evidence based clinical recommendations with large language models
di: Li, Dubai, et al.
Pubblicazione: (2025)

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
di: Zhou, Yujun, et al.
Pubblicazione: (2025)

Retrieval augmentation of large language models for lay language generation
di: Guo, Yue, et al.
Pubblicazione: (2022)