MultiNLI
PulseAugur coverage of MultiNLI — every cluster mentioning MultiNLI across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
LoRA fine-tuning technique explained for large language models
A new post explains LoRA, a technique for efficiently fine-tuning large language models like GPT-3. LoRA avoids the need to store a full model copy for each task by training only two smaller matrices, A and B, which rep…
-
New framework improves NLU model robustness via failure-mode bandits
Researchers have developed a novel adversarial data curation framework designed to enhance the robustness of natural language understanding models. This system frames data curation as a failure-mode contextual bandit pr…
-
NLI label variation study fails to replicate prior findings
A preregistered replication study on the Stanford Natural Language Inference corpus, MultiNLI, and ChaosNLI datasets has failed to confirm prior findings regarding human label variation. The original research suggested …
-
NLI label variation study fails to replicate prior findings on monotonicity
A preregistered replication study aimed to verify a previously observed boundary in human label variation (HLV) within natural language inference (NLI) tasks. The original study suggested that hypotheses with non-upward…