LLM Parser

Overview

Textkernel offers a resume parsing option that seamlessly integrates the power of Large Language Models (LLMs) with Textkernel technology. The result is a parser that is better than can be built with each technology individually.

The LLM Parser can be enabled on a per-request basis by setting the request parameter UseLLMParser to true. Additionally, the LLM Parser can be tested on the Demo site by toggling Enable LLM Parser on the options page. An add-on cost applies to each transaction that has the LLM Parser enabled.

Limitations and Caveats

• All fields mentioned in the low-usage fields document are not output.

• Additionally, the following fields are not output:

  • Individual education raw text
  • Normalized local and international degree codes/descriptions
  • Individual position descriptions

• Responses can be several seconds slower when using the LLM Parser.

• The LLM Parser can generate information that is factually incorrect or misleading. It may also output plausible-sounding but false information. However, the LLM Parser offers improved accuracy compared to the standard parser, helping to offset any potential hallucinations.
• In exceptional cases, the LLM Parser returns an error or takes more than 60 seconds to respond. In such cases, we automatically fall back to our standard parser. The add-on credits for using the LLM parser will still be applied.

Frequently Asked Questions

Check our LLM Parser FAQ