Datasets/lm evaluation library

[RakshitKhajuria]

Description

This PR aims at adding Benchmark Datasets For QA task

Datasets Added:

• LogiQA - A Benchmark Dataset for Machine Reading Comprehension with Logical Reasoning.

• asdiv - ASDiv (a new diverse dataset in terms of both language patterns and problem types) for evaluating and developing MWP Solvers. It contains 2305 english Math Word Problems (MWPs), and is published in this paper "A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers".

• Google/Bigbench - The Beyond the Imitation Game Benchmark (BIG-bench) is a collaborative benchmark intended to probe large language models and extrapolate their future capabilities. Tasks included in BIG-bench are summarized by keyword here, and by task name here

  We added some of the subsets to our library:
    1. AbstractUnderstanding
    2. DisambiguationQA
    3. Disfil qa
    4. Casual Judgement
  

---

➤ Fixes: Explore lm evaluation library for good datasets #556

➤ Notebook Links:

• BigBench
• LogiQA
• asdiv

Type of change

Please delete options that are not relevant.

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

Usage

Checklist:

• I've added Google style docstrings to my code.
• I've used pydantic for typing when/where necessary.
• I have linted my code
• I have added tests to cover my changes.

Screenshots (if appropriate):

LogiQA

ASDiv

BigBench

[ArshaanNazir]

@RakshitKhajuria @Prikshit7766 have you prepared any NB for it. Give link to NB in PR description with some screenshots of generated results.

[RakshitKhajuria]

NB for it. Give link to NB in PR description with some screenshots of generated results.

Updated