| 1 |
VISTA: Visualization of Token Attribution via Efficient Analysis |
VISTA:提出一种高效分析的Token归因可视化方法,用于理解LLM的信息处理方式。 |
large language model |
✅ |
|
| 2 |
LLM-as-a-Judge for Time Series Explanations |
提出基于LLM的无参考时间序列解释评估方法,解决现有评估方法依赖参考解释的问题。 |
large language model |
|
|
| 3 |
RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale |
RuleForge:大规模自动化生成和验证Web漏洞检测规则 |
large language model |
|
|
| 4 |
ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models |
ThinknCheck:提出一种基于紧凑、可解释模型的、推理驱动的、可信的声明验证方法。 |
chain-of-thought |
|
|