Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

• URL: http://arxiv.org/abs/2311.08648v4
• Date: Sun, 16 Jun 2024 01:28:49 GMT
• Title: Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
• Authors: Yuhang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An, Wei Ai, Furong Huang,
• Abstract summary: Language models (LMs) have achieved notable success in numerous NLP tasks. They face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations.
• Score: 28.832684088975622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. Previous research has primarily concentrated on word, phrase, and syntax features, neglecting the concept level, often due to the absence of concept labels and difficulty in identifying conceptual content in input texts. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations. Our method's efficacy, surpassing traditional token removal approaches, is validated through extensive testing.

Related papers

• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Improving Input-label Mapping with Demonstration Replay for In-context Learning [67.57288926736923]
  In-context learning (ICL) is an emerging capability of large autoregressive language models. We propose a novel ICL method called Sliding Causal Attention (RdSca) We show that our method significantly improves the input-label mapping in ICL demonstrations.
  arXiv  Detail & Related papers  (2023-10-30T14:29:41Z)
• Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary [65.268245109828]
  Non-human-like behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon is the generation of inconsistent predictions, which produces contradictory results. We propose a practical approach that alleviates the inconsistent behaviour issue by improving PLM awareness.
  arXiv  Detail & Related papers  (2023-10-24T06:15:15Z)
• IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations [11.008412414253662]
  Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Recent studies have shown that LLMs tend to generate unintended, inconsistent, or wrong texts as outputs. We propose a novel ensemble learning method, Interpretable Ensemble Representation Learning (IERL), that systematically combines LLM and crowdsourced knowledge representations.
  arXiv  Detail & Related papers  (2023-06-24T05:02:34Z)
• Larger language models do in-context learning differently [93.90674531127559]
  In-context learning (ICL) in language models is affected by semantic priors versus input-label mappings. We investigate two setups-ICL with flipped labels and ICL with semantically-unrelated labels.
  arXiv  Detail & Related papers  (2023-03-07T12:24:17Z)
• ConNER: Consistency Training for Cross-lingual Named Entity Recognition [96.84391089120847]
  Cross-lingual named entity recognition suffers from data scarcity in the target languages. We propose ConNER as a novel consistency training framework for cross-lingual NER.
  arXiv  Detail & Related papers  (2022-11-17T07:57:54Z)
• Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation [44.319739489968164]
  Deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks. In this study, we focus on the spurious correlation between word features and labels that models learn from the biased data distribution. We propose a training strategy Less-Learn-Shortcut (LLS): our strategy quantifies the biased degree of the biased examples and down-weights them accordingly.
  arXiv  Detail & Related papers  (2022-05-25T09:08:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.