Common Sense Reasoning On Commonsenseqa

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称	Accuracy	Paper Title	Repository
DEKCOR	83.3	Fusing Context Into Knowledge Graph for Commonsense Question Answering
UnifiedQA 11B (fine-tuned)	79.1	UnifiedQA: Crossing Format Boundaries With a Single QA System
RoBERTa+HyKAS Ma et al. (2019)	73.2	Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering	-
Chain of thought ASDiv	28.6	Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
KagNet	58.9	KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
OPT 66B (1-shot)	66.4	BloombergGPT: A Large Language Model for Finance	-
GPT-4o (HPT)	92.54	Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles	-
UnifiedQA 440M (fine-tuned)	64	UnifiedQA: Crossing Format Boundaries With a Single QA System
UL2 20B (chain-of-thought)	51.4	UL2: Unifying Language Learning Paradigms
STaR without Rationalization (on GPT-J)	68.8	STaR: Bootstrapping Reasoning With Reasoning
Few-shot CoT GPT-J	36.6	STaR: Bootstrapping Reasoning With Reasoning
PaLM 2 (few‑shot, CoT, SC)	90.4	PaLM 2 Technical Report
T5-XXL 11B (fine-tuned)	78.1	UnifiedQA: Crossing Format Boundaries With a Single QA System
RoBERTa-Large 355M	72.1	RoBERTa: A Robustly Optimized BERT Pretraining Approach
GPT-3 Direct Finetuned	73.0	Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
BLOOM 176B (1-shot)	64.2	BloombergGPT: A Large Language Model for Finance	-
UL2 20B (zero-shot)	34.2	UL2: Unifying Language Learning Paradigms
DeBERTaV3-large+KEAR	91.2	Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
DRAGON	78.2	Deep Bidirectional Language-Knowledge Graph Pretraining
BERT_CSlarge	62.2	Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models	-

0 of 38 row(s) selected.