A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension

• URL: http://arxiv.org/abs/2209.01824v2
• Date: Wed, 6 Sep 2023 04:08:08 GMT
• Title: A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension
• Authors: Xanh Ho, Johannes Mario Meissner, Saku Sugawara, and Akiko Aizawa
• Abstract summary: We focus on the field of machine reading comprehension (MRC), an important task for showcasing high-level language understanding. We highlight two concerns for shortcut mitigation in MRC: (1) the lack of public challenge sets, a necessary component for effective and reusable evaluation, and (2) the lack of certain mitigation techniques that are prominent in other areas.
• Score: 34.400234717524306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The issue of shortcut learning is widely known in NLP and has been an important research focus in recent years. Unintended correlations in the data enable models to easily solve tasks that were meant to exhibit advanced language understanding and reasoning capabilities. In this survey paper, we focus on the field of machine reading comprehension (MRC), an important task for showcasing high-level language understanding that also suffers from a range of shortcuts. We summarize the available techniques for measuring and mitigating shortcuts and conclude with suggestions for further progress in shortcut research. Importantly, we highlight two concerns for shortcut mitigation in MRC: (1) the lack of public challenge sets, a necessary component for effective and reusable evaluation, and (2) the lack of certain mitigation techniques that are prominent in other areas.

Related papers

• Shortcut Learning in In-Context Learning: A Survey [17.19214732926589]
  Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks. This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL)
  arXiv  Detail & Related papers  (2024-11-04T12:13:04Z)
• The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends [64.99423243200296]
  Conversation Analysis (CA) strives to uncover and analyze critical information from conversation data. In this paper, we perform a thorough review and systematize CA task to summarize the existing related work. We derive four key steps of CA from conversation scene reconstruction, to in-depth attribution analysis, and then to performing targeted training, finally generating conversations.
  arXiv  Detail & Related papers  (2024-09-21T16:52:43Z)
• Robustness Assessment of Mathematical Reasoning in the Presence of Missing and Contradictory Conditions [48.251724997889184]
  We develop a benchmark called Problems with Missing and Contradictory conditions (PMC) We introduce two novel metrics to evaluate the performance of few-shot prompting methods in these scenarios. We propose a novel few-shot prompting method called SMT-LIB Prompting (SLP), which utilizes the SMT-LIB language to model the problems instead of solving them directly.
  arXiv  Detail & Related papers  (2024-06-07T16:24:12Z)
• Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery [12.608345627859322]
  We propose a shortcuts-fused Selective Rationalization (SSR) method, which boosts the rationalization by discovering and exploiting potential shortcuts. Specifically, SSR first designs a shortcuts discovery approach to detect several potential shortcuts. Then, by introducing the identified shortcuts, we propose two strategies to mitigate the problem of utilizing shortcuts to compose rationales.
  arXiv  Detail & Related papers  (2024-03-12T07:24:17Z)
• Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks [11.197027472291905]
  We propose a two-stage framework for NKI tasks, named PGRA. In the first stage, we adopt a task-agnostic retriever to build a shared static index and select candidate evidence efficiently. In the second stage, we design a prompt-guided reranker to rerank the nearest evidence according to task-specific relevance for the reader.
  arXiv  Detail & Related papers  (2023-05-28T07:27:12Z)
• Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning [28.162661418161466]
  Large language models (LLMs) have recently shown great potential for in-context learning. This paper investigates the reliance of LLMs on shortcuts or spurious correlations within prompts. We uncover a surprising finding that larger models are more likely to utilize shortcuts in prompts during inference.
  arXiv  Detail & Related papers  (2023-05-26T20:56:30Z)
• Parsing Objects at a Finer Granularity: A Survey [54.72819146263311]
  Fine-grained visual parsing is important in many real-world applications, e.g., agriculture, remote sensing, and space technologies. Predominant research efforts tackle these fine-grained sub-tasks following different paradigms. We conduct an in-depth study of the advanced work from a new perspective of learning the part relationship.
  arXiv  Detail & Related papers  (2022-12-28T04:20:10Z)
• Why Machine Reading Comprehension Models Learn Shortcuts? [56.629192589376046]
  We argue that larger proportion of shortcut questions in training data make models rely on shortcut tricks excessively. A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions.
  arXiv  Detail & Related papers  (2021-06-02T08:43:12Z)
• Retrospective Reader for Machine Reading Comprehension [90.6069071495214]
  Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder. This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions.
  arXiv  Detail & Related papers  (2020-01-27T11:14:34Z)

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.