KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level
Hallucination Detection

KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

13 October 2023

ArXiv (abs)PDF HTML

Papers citing "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection"

9 / 9 papers shown

Title
Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation Keyu Zhao Fengli Xu Yong Li LRM 105 0 0 05 Jun 2025
Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling Xinglin Wang Yiwei Li Shaoxiong Feng Peiwen Yuan Y. Zhang Jiayi Shi Chuyi Tan Boyuan Pan Yao Hu Kan Li LRM 15 0 0 30 May 2025
Think Only When You Need with Large Hybrid-Reasoning Models Lingjie Jiang Xun Wu Shaohan Huang Qingxiu Dong Zewen Chi Li Dong Xingxing Zhang Tengchao Lv Lei Cui Furu Wei OffRL LRM 157 5 0 20 May 2025
ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates L. Yang Zhaochen Yu Tengjiao Wang Mengdi Wang ReLM LRM AI4CE 181 18 0 10 Feb 2025
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models Yanwen Huang Yong Zhang Ning Cheng Zhitao Li Shaojun Wang Jing Xiao 176 0 0 02 Jan 2025
ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty Qing Zong Zhaoxiang Wang Tianshi Zheng Xiyu Ren Yangqiu Song 155 3 0 28 Dec 2024
Edit-Constrained Decoding for Sentence Simplification Tatsuya Zetsu Yuki Arase Tomoyuki Kajiwara 53 0 0 28 Sep 2024
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval Siwei Wu Yizhi Li Kang Zhu Ge Zhang Yiming Liang ... Wenhu Chen Wenhao Huang Noura Al Moubayed Jie Fu Chenghua Lin 98 13 0 24 Jan 2024
Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access Saibo Geng Berkay Döner Chris Wendler Martin Josifoski Robert West 107 4 0 18 Jan 2024

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.