Shadowgraph
TrendingBuzzTop stargazers
Chrome extension
Sign in

ErikYip/LLM-Uncertainty-Bench

Dataset

Datasets comprising 10,000 instances each used for uncertainty quantification in LLMs.

0

5 commits

1 linked in READMEs

updated Jan 25, 2024

See the code

README

Datasets comprising 10,000 instances each used for uncertainty quantification in LLMs.

  1. mmlu_10k is used for question answering.
  2. cosmosqa_10k is used for reading comprehension.
  3. hellaswag_10k is used for commonsense inference.
  4. halu_dialogue is used for dialogue response selection.
  5. halu_summarization is used for document summarization.

For more details on how these datasets are utilized, check out our github repo: https://github.com/smartyfh/LLM-Uncertainty-Bench/tree/main

Similar repos

smartyfh/LLM-Uncertainty-Bench

Benchmarking LLMs via Uncertainty Quantification

263

leobeeson/llm_benchmarks

A collection of benchmarks and datasets for evaluating LLM.

581

shuaishuaicdp/MLLM-Judge

Dataset

4

UUUserna/OSR-Bench

Dataset

4

lmmlzn/Awesome-LLMs-Datasets

Summarize existing representative LLMs text datasets.

1,480

wgwang/awesome-LLM-benchmarks

Awesome LLM Benchmarks to evaluate the LLMs across text, code, image, audio, video and more.

169

facebook/AbstentionBench

Dataset

AbstentionBench: A Holistic Benchmark for LLM Abstention

7

chengpingan/CoConflictQA

Dataset

CoConflictQA is a benchmark designed to evaluate the contextual faithfulness of Large Language…

0

Linked in READMEs

smartyfh/LLM-Uncertainty-Bench

Benchmarking LLMs via Uncertainty Quantification

263

README badge

ErikYip/LLM-Uncertainty-Bench

Dataset

Datasets comprising 10,000 instances each used for uncertainty quantification in LLMs.

0

5 commits

1 linked in READMEs

updated Jan 25, 2024

See the code

README

Datasets comprising 10,000 instances each used for uncertainty quantification in LLMs.

  1. mmlu_10k is used for question answering.
  2. cosmosqa_10k is used for reading comprehension.
  3. hellaswag_10k is used for commonsense inference.
  4. halu_dialogue is used for dialogue response selection.
  5. halu_summarization is used for document summarization.

For more details on how these datasets are utilized, check out our github repo: https://github.com/smartyfh/LLM-Uncertainty-Bench/tree/main

Similar repos

smartyfh/LLM-Uncertainty-Bench

Benchmarking LLMs via Uncertainty Quantification

263

leobeeson/llm_benchmarks

A collection of benchmarks and datasets for evaluating LLM.

581

shuaishuaicdp/MLLM-Judge

Dataset

4

UUUserna/OSR-Bench

Dataset

4

lmmlzn/Awesome-LLMs-Datasets

Summarize existing representative LLMs text datasets.

1,480

wgwang/awesome-LLM-benchmarks

Awesome LLM Benchmarks to evaluate the LLMs across text, code, image, audio, video and more.

169

facebook/AbstentionBench

Dataset

AbstentionBench: A Holistic Benchmark for LLM Abstention

7

chengpingan/CoConflictQA

Dataset

CoConflictQA is a benchmark designed to evaluate the contextual faithfulness of Large Language…

0

Linked in READMEs

smartyfh/LLM-Uncertainty-Bench

Benchmarking LLMs via Uncertainty Quantification

263

README badge