paper-with-me

Papers

Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference

2024-10-11 · Grace Proebsting, Adam Poliak

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.

📄 PDF Abstract BibTeX arXiv:2410.08996

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelNatural Language Inference

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference

2019-07-09 · SEMEVAL 2019 6 · Yonatan Belinkov, Adam Poliak, Stuart M. Shieber, Benjamin Van Durme 외

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 Inference

Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference

2019-07-09 · ACL 2019 7 · Yonatan Belinkov, Adam Poliak, Stuart M. Shieber, Benjamin Van Durme 외

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 Inference

On the Thinking-Language Modeling Gap in Large Language Models

2025-05-19 · Chenxi Liu, Yongqiang Chen, Tongliang Liu, James Cheng 외

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 Modelling

Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models

2025-05-25 · Seunguk Yu, Juhwan Choi, Youngbin Kim

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 …

Articles

Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference

2021-01-19 · Qingyuan Hu, Yi Zhang, Kanishka Misra, Julia Rayz

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