Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference
We test whether replacing crowdsource workers with LLMs to write Natural Language Inference (NLI) hypotheses similarly results in annotation artifacts. We recreate a portion of the Stanford NLI corpus using GPT-4, Llama-2 and Mistral 7b, and train hypothesis-only classifiers to determine whether LLM-elicited hypotheses contain annotation artifacts. On our LLM-elicited NLI datasets, BERT-based hypothesis-only classifiers achieve between 86-96% accuracy, indicating these datasets contain hypothesis-only artifacts. We also find frequent "give-aways" in LLM-generated hypotheses, e.g. the phrase "swimming in a pool" appears in more than 10,000 contradictions generated by GPT-4. Our analysis provides empirical evidence that well-attested biases in NLI can persist in LLM-generated data.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelNatural Language InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate wheth…
Natural Language InferenceDon't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
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 prob…
Natural Language InferenceOn the Thinking-Language Modeling Gap in Large Language Models
System 2 reasoning is one of the defining characteristics of intelligence, which requires slow and logical thinking. Human conducts System 2 reasoning via the language of thoughts that organizes the reasoning process as …
Language ModelingLanguage ModellingDelving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models
Despite the recent strides in large language models, studies have underscored the existence of social biases within these systems. In this paper, we delve into the validation and comparison of the ethical biases of LLMs …
ArticlesExploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference
Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) is the task of predicting the entailment relation between a pair of sentences (premise and hypothesis). This task has been described as a valuable …
Natural Language InferenceNatural Language UnderstandingRTE