Slot Filling Method Performance Compared to LLMs with Refined Prompts and Fine-Tuned Phi-4

A dataset comparing the performance of a slot filling method against large language models in zero-shot learning scenarios. The data includes results from initial and refined prompts, as well as a fine-tuned version of the Phi-4 model. The dataset was authored by Pegah Safari and last updated on 2026-05-11.

Use Cases

• Benchmarking slot filling methods against large language models based on performance metrics.
• Evaluating the impact of prompt refinement on zero-shot learning performance.
• Comparing fine-tuned small models like Phi-4 with larger zero-shot LLMs.
• Analyzing the effectiveness of different prompting strategies for information extraction tasks.

Strengths

• Data is licensed under CC-BY-4.0, allowing for broad reuse.
• The dataset is small (5.5 KB), facilitating quick download and inspection.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

Pegah Safari via figshare

Freshness

Last updated 2026-05-11 17:27:45; freshness should be verified.