mirror of
https://github.com/deepseek-ai/DeepSeek-LLM.git
synced 2026-11-05 00:57:25 +00:00
[GH-ISSUE #100] [Bug] 模型输出末尾偶现无意义HTML/XML标签乱码(如 </h3>、</output>、</thinking>) #77
Labels
No labels
bug
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-LLM#77
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @ciallo0721-cmd on GitHub (Jul 20, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/100
Description:
在正常对话过程中,DeepSeek模型有概率在回答的末尾附加无意义的HTML/XML标签类乱码内容,包括但不限于:
</h3> </h3> </h3> ...(大量重复)</output></thinking>这些标签与对话内容完全无关,不属于正常回答的一部分,影响了用户体验和输出内容的可用性(尤其是在需要复制粘贴完整回答的场景下)。
实际案例(含分享链接):
Expected Behavior:
模型应仅输出与用户问题相关的内容,末尾不应附加任何无关的HTML/XML标签或重复字符。
Actual Behavior:
模型在回答末尾随机附加无意义标签,例如:
</h3>重复数十次</output></thinking>Environment:
该问题虽不涉及安全或隐私泄露,但会降低输出质量,影响用户对模型回答的信任度和可用性。建议将其纳入后续模型优化计划。
Discovered by: ciallo0721-cmd
Reported via: GitHub Issue
@ciallo0721-cmd commented on GitHub (Jul 20, 2026):