Natural Language Inference On Anli Test

评估指标

评测结果

各个模型在此基准测试上的表现结果

模型名称	A1	A2	A3	Paper Title	Repository
ChatGPT	62.3	52.6	54.1	A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets
GPT-3	36.8	34	40.2	Language Models are Few-Shot Learners
PaLM 2-S (one-shot)	53.1	48.8	53.2	PaLM 2 Technical Report
T0-11B (explanation prompting)	75.6	60.6	59.9	Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}	-
KiC-770M	36.30	35.00	37.60	Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models	-
BLOOM 176B (one-shot)	33.6	33.8	35.17	BloombergGPT: A Large Language Model for Finance	-
OPT 66B (one-shot)	33.1	34.2	34.92	BloombergGPT: A Large Language Model for Finance	-
PaLM 540B (Self Consistency)	-	64.5	63.4	Large Language Models Can Self-Improve	-
PaLM 540B (Self Improvement, Self Consistency)	-	66.5	67.9	Large Language Models Can Self-Improve	-
RoE-3B	35.49	34.64	31.22	Exploring the Benefits of Training Expert Language Models over Instruction Tuning
GPT-NeoX (one-shot)	32.6	33.8	36.17	BloombergGPT: A Large Language Model for Finance	-
T5-3B (explanation prompting)	81.8	72.5	74.8	Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}	-
InfoBERT (RoBERTa)	75	50.5	47.7	InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective
PaLM 2-L (one-shot)	73.1	63.4	67.1	PaLM 2 Technical Report
T0-3B (CoT fine-tuned)	41.7	37.2	41.9	The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning	-
PaLM 540B (CoT Prompting)	-	58.9	60.6	Large Language Models Can Self-Improve	-
RoBERTa (Large)	72.4	49.8	44.4	RoBERTa: A Robustly Optimized BERT Pretraining Approach
PaLM 540B (Self Improvement, Standard-Prompting)	-	64.8	66.9	Large Language Models Can Self-Improve	-
Bloomberg GPT (one-shot)	32.9	34.4	37.33	BloombergGPT: A Large Language Model for Finance	-
XLNet (Large)	70.3	50.9	49.4	XLNet: Generalized Autoregressive Pretraining for Language Understanding

0 of 25 row(s) selected.