paper-with-me

Papers

SED: Self-Evaluation Decoding Enhances Large Language Models for Better Generation

2024-05-26 · Ziqin Luo, Haixia Han, Haokun Zhao, Guochao Jiang, Chengyu Du, Tingyun Li, Jiaqing Liang, Deqing Yang, Yanghua Xiao

Existing Large Language Models (LLMs) generate text through unidirectional autoregressive decoding methods to respond to various user queries. These methods tend to consider token selection in a simple sequential manner, making it easy to fall into suboptimal options when encountering uncertain tokens, referred to as chaotic points in our work. Many chaotic points exist in texts generated by LLMs, and they often significantly affect the quality of subsequently generated tokens, which can interfere with LLMs' generation. This paper proposes Self-Evaluation Decoding, SED, a decoding method for enhancing model generation. Analogous to the human decision-making process, SED integrates speculation and evaluation steps into the decoding process, allowing LLMs to make more careful decisions and thus optimize token selection at chaotic points. Experimental results across various tasks using different LLMs demonstrate SED's effectiveness.

📄 PDF Abstract BibTeX arXiv:2405.16552

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Integrative Decoding: Improve Factuality via Implicit Self-consistency

2024-10-02 · Yi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao 외

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of lar…

TruthfulQA

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models

2024-11-01 · Jianyi Zhang, Da-Cheng Juan, Cyrus Rashtchian, Chun-Sung Ferng 외

Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Logits Evolution Decoding (SLED), a novel d…

Mixture-of-Experts

DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models

2025-03-05 · YiQiu Guo, Yuchen Yang, Zhe Chen, Pingjie Wang 외

The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation. Existing solutions either underutilize mo…

HallucinationText Generation

Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models

2025-10-15 · Eun Woo Im, Muhammad Kashif Ali, Vivek Gupta arxiv

Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal capabilities, but they inherit the tendency to hallucinate from their underlying language models. While visual contrastive decoding has been pr…

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions

2024-08-14 · Quan Liu, Zhenhong Zhou, Longzhu He, Yi Liu 외

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objec…

Safety Alignment