We test whether NLP datasets created with Large Language Models (LLMs) contain annotation artifacts and social biases like NLP datasets elicited from crowd-source workers. We recreate a portion of the Stanford Natural Language Inference corpus using GPT-4, Llama-2 70b for Chat, and Mistral 7b Instruct. We train hypothesis-only classifiers to determine whether LLM-elicited NLI datasets contain annotation artifacts. Next, we use point-wise mutual information to identify the words in each dataset that are associated with gender, race, and age-related terms. On our LLM-generated NLI datasets, fine-tuned BERT hypothesis-only classifiers achieve between 86-96% accuracy. Our analyses further characterize the annotation artifacts and stereotypical biases in LLM-generated datasets.

We introduce Uncertain Natural Language Inference (UNLI), a refinement of Natural Language Inference (NLI) that shifts away from categorical labels, targeting instead the direct prediction of subjective probability assessments.We demonstrate the feasibility of collecting annotations for UNLI by relabeling a portion of the SNLI dataset under a probabilistic scale, where items even with the same categorical label differ in how likely people judge them to be true given a premise.We describe a direct scalar regression modeling approach, and find that existing categorically labeled NLI data can be used in pre-training.Our best models approach human performance, demonstrating models may be capable of more subtle inferences than the categorical bin assignment employed in current NLI tasks.

Natural Language Inference (NLI) datasets often contain hypothesis-only biases-artifacts that allow models to achieve non-trivial performance without learning whether a premise entails a hypothesis.We propose two probabilistic methods to build models that are more robust to such biases and better transfer across datasets.In contrast to standard approaches to NLI, our methods predict the probability of a premise given a hypothesis and NLI label, discouraging models from ignoring the premise.We evaluate our methods on synthetic and existing NLI datasets by training on datasets containing biases and testing on datasets containing no (or different) hypothesis-only biases.Our results indicate that these methods can make NLI models more robust to dataset-specific artifacts, transferring better than a baseline architecture in 9 out of 12 NLI datasets.Additionally, we provide an extensive analysis of the interplay of our methods with known biases in NLI datasets, as well as the effects of encouraging models to ignore biases and fine-tuning on target datasets.1 * * Equal contribution 1 Our code is available at https://github.com/ azpoliak/robust-nli.2 This hypothesis contradicts the premise and would likely not be inferred.

Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White, Benjamin Van Durme. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.

The semantic function tags of Bonial, Stowe, and Palmer (2013) and the ordinal, multi-property annotations of Reisinger et al. (2015) draw inspiration from Ddowty's semantic proto-role theory. We approach proto-role labeling as a multi-label classification problem and establish strong results for the task by adapting a successful model of traditional semantic role labeling. We achieve a proto-role micro-averaged F1 of 81.7 using gold syntax and explore joint and conditional models of proto-roles and categorical roles. In comparing the effect of Bonial, Stowe, and Palmer's tags to PropBank ArgN-style role labels, we are surprised that neither annotations greatly improve proto-role prediction; however, we observe that ArgN models benefit much from observed syntax and from observed or modeled proto-roles while our models of the semantic function tags do not.