HANS, are you clever? Clever Hans Effect Analysis of Neural Systems

• URL: http://arxiv.org/abs/2309.12481v2
• Date: Thu, 2 May 2024 06:36:26 GMT
• Title: HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
• Authors: Leonardo Ranaldi, Fabio Massimo Zanzotto,
• Abstract summary: Large Language Models (It-LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively. Several multiple-choice questions (MCQ) benchmarks have been proposed to construct solid assessments of the models' abilities. However, earlier works are demonstrating the presence of inherent "order bias" in It-LLMs, posing challenges to the appropriate evaluation.
• Score: 1.6267479602370545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Instruction-tuned Large Language Models (It-LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively. In fact, several multiple-choice questions (MCQ) benchmarks have been proposed to construct solid assessments of the models' abilities. However, earlier works are demonstrating the presence of inherent "order bias" in It-LLMs, posing challenges to the appropriate evaluation. In this paper, we investigate It-LLMs' resilience abilities towards a series of probing tests using four MCQ benchmarks. Introducing adversarial examples, we show a significant performance gap, mainly when varying the order of the choices, which reveals a selection bias and brings into discussion reasoning abilities. Following a correlation between first positions and model choices due to positional bias, we hypothesized the presence of structural heuristics in the decision-making process of the It-LLMs, strengthened by including significant examples in few-shot scenarios. Finally, by using the Chain-of-Thought (CoT) technique, we elicit the model to reason and mitigate the bias by obtaining more robust models.

Related papers

• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• Reasoning Beyond Bias: A Study on Counterfactual Prompting and Chain of Thought Reasoning [0.0]
  We show that differences in learned regularities across answer options are predictive of model preferences and mirror human test-taking strategies. We introduce two novel methods: Counterfactual Prompting with Chain of Thought (CoT) and Counterfactual Prompting with Agnostically Primed CoT (APriCoT) Our results suggest that mitigating bias requires a "System-2" like process and that CoT reasoning is susceptible to confirmation bias under some prompting methodologies.
  arXiv  Detail & Related papers  (2024-08-16T10:34:50Z)
• Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning [14.569770617709073]
  We present a detailed analysis of which design choices cause instabilities and inconsistencies in task predictions. We show how spurious correlations between input distributions and labels form only a minor problem for prompted models. We statistically analyse the results to show which factors are the most influential, interactive or stable.
  arXiv  Detail & Related papers  (2023-10-20T13:25:24Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• Cross Feature Selection to Eliminate Spurious Interactions and Single Feature Dominance Explainable Boosting Machines [0.0]
  Interpretability is essential for legal, ethical, and practical reasons. High-performance models can suffer from spurious interactions with redundant features and single-feature dominance. In this paper, we explore novel approaches to address these issues by utilizing alternate Cross-feature selection, ensemble features and model configuration alteration techniques.
  arXiv  Detail & Related papers  (2023-07-17T13:47:41Z)
• Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models [3.9052860539161918]
  We propose a simple method for measuring a scale of models' reliance on any identified spurious feature. We assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA) We find that while existing debiasing methods can mitigate reliance on a chosen spurious feature, the OOD performance gains of these methods can not be explained by mitigated reliance on biased features.
  arXiv  Detail & Related papers  (2023-05-11T14:35:00Z)
• Knowledge-Based Counterfactual Queries for Visual Question Answering [0.0]
  We propose a systematic method for explaining the behavior and investigating the robustness of VQA models through counterfactual perturbations. For this reason, we exploit structured knowledge bases to perform deterministic, optimal and controllable word-level replacements targeting the linguistic modality. We then evaluate the model's response against such counterfactual inputs.
  arXiv  Detail & Related papers  (2023-03-05T08:00:30Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Are Neural Topic Models Broken? [81.15470302729638]
  We study the relationship between automated and human evaluation of topic models. We find that neural topic models fare worse in both respects compared to an established classical method.
  arXiv  Detail & Related papers  (2022-10-28T14:38:50Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Counterfactual Variable Control for Robust and Interpretable Question Answering [57.25261576239862]
  Deep neural network based question answering (QA) models are neither robust nor explainable in many cases. In this paper, we inspect such spurious "capability" of QA models using causal inference. We propose a novel approach called Counterfactual Variable Control (CVC) that explicitly mitigates any shortcut correlation.
  arXiv  Detail & Related papers  (2020-10-12T10:09:05Z)

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.