Look at the First Sentence: Position Bias in Question Answering

• URL: http://arxiv.org/abs/2004.14602v4
• Date: Mon, 8 Mar 2021 15:09:45 GMT
• Title: Look at the First Sentence: Position Bias in Question Answering
• Authors: Miyoung Ko, Jinhyuk Lee, Hyunjae Kim, Gangwoo Kim, Jaewoo Kang
• Abstract summary: We study position bias in question answering models such as BiDAF and BERT. We train models with various de-biasing methods including entropy regularization and bias ensembling. We find that using the prior distribution of answer positions as a bias model is very effective at reducing position bias.
• Score: 21.532952595659705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many extractive question answering models are trained to predict start and end positions of answers. The choice of predicting answers as positions is mainly due to its simplicity and effectiveness. In this study, we hypothesize that when the distribution of the answer positions is highly skewed in the training set (e.g., answers lie only in the k-th sentence of each passage), QA models predicting answers as positions can learn spurious positional cues and fail to give answers in different positions. We first illustrate this position bias in popular extractive QA models such as BiDAF and BERT and thoroughly examine how position bias propagates through each layer of BERT. To safely deliver position information without position bias, we train models with various de-biasing methods including entropy regularization and bias ensembling. Among them, we found that using the prior distribution of answer positions as a bias model is very effective at reducing position bias, recovering the performance of BERT from 37.48% to 81.64% when trained on a biased SQuAD dataset.

Related papers

• Making Bias Non-Predictive: Training Robust LLM Judges via Reinforcement Learning [91.8584139564909]
  Large language models (LLMs) increasingly serve as automated judges, yet they remain susceptible to cognitive biases.<n>We propose Epistemic Independence Training (EIT), a reinforcement learning framework grounded in a key principle.<n>EIT operationalizes this through a balanced conflict strategy where bias signals are equally likely to support correct and incorrect answers.
  arXiv  Detail & Related papers  (2026-02-02T01:43:48Z)
• A Causal Information-Flow Framework for Unbiased Learning-to-Rank [52.54102347581931]
  In web search and recommendation systems, user clicks are widely used to train ranking models.<n>We introduce a novel causal learning-based ranking framework that extends Unbiased Learning-to-Rank.<n>Our method consistently reduces measured bias leakage and improves ranking performance.
  arXiv  Detail & Related papers  (2026-01-09T07:19:35Z)
• Positional Bias in Binary Question Answering: How Uncertainty Shapes Model Preferences [8.389558188293641]
  We quantify and analyze positional bias across five large language models under varying degrees of answer uncertainty.<n>We observe that positional bias is nearly absent under low-uncertainty conditions, but grows exponentially when it becomes doubtful to decide which option is correct.
  arXiv  Detail & Related papers  (2025-06-30T11:30:23Z)
• Correcting for Position Bias in Learning to Rank: A Control Function Approach [9.986244291715762]
  We propose a novel control function-based method that accounts for position bias in a two-stage process.<n>Unlike previous position bias correction methods, our method does not require knowledge of the click or propensity model.<n> Experimental results demonstrate that our method outperforms state-of-the-art approaches in correcting for position bias.
  arXiv  Detail & Related papers  (2025-06-08T04:10:14Z)
• Eliminating Position Bias of Language Models: A Mechanistic Approach [119.34143323054143]
  Position bias has proven to be a prevalent issue of modern language models (LMs) Our mechanistic analysis attributes the position bias to two components employed in nearly all state-of-the-art LMs: causal attention and relative positional encodings. By eliminating position bias, models achieve better performance and reliability in downstream tasks, including LM-as-a-judge, retrieval-augmented QA, molecule generation, and math reasoning.
  arXiv  Detail & Related papers  (2024-07-01T09:06:57Z)
• Mitigate Position Bias in Large Language Models via Scaling a Single Dimension [47.792435921037274]
  This paper first explores the micro-level manifestations of position bias, concluding that attention weights are a micro-level expression of position bias. It further identifies that, in addition to position embeddings, causal attention mask also contributes to position bias by creating position-specific hidden states. Based on these insights, we propose a method to mitigate position bias by scaling this positional hidden states.
  arXiv  Detail & Related papers  (2024-06-04T17:55:38Z)
• Projective Methods for Mitigating Gender Bias in Pre-trained Language Models [10.418595661963062]
  Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters. We find that projective methods can be effective at both intrinsic bias and downstream bias mitigation, but that the two outcomes are not necessarily correlated.
  arXiv  Detail & Related papers  (2024-03-27T17:49:31Z)
• Mitigating Bias for Question Answering Models by Tracking Bias Influence [84.66462028537475]
  We propose BMBI, an approach to mitigate the bias of multiple-choice QA models. Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance. We show that our method could be applied to multiple QA formulations across multiple bias categories.
  arXiv  Detail & Related papers  (2023-10-13T00:49:09Z)
• Large Language Models Are Not Robust Multiple Choice Selectors [117.72712117510953]
  Multiple choice questions (MCQs) serve as a common yet important task format in the evaluation of large language models (LLMs) This work shows that modern LLMs are vulnerable to option position changes due to their inherent "selection bias" We propose a label-free, inference-time debiasing method, called PriDe, which separates the model's prior bias for option IDs from the overall prediction distribution.
  arXiv  Detail & Related papers  (2023-09-07T17:44:56Z)
• Single-Sentence Reader: A Novel Approach for Addressing Answer Position Bias [0.40792653193642503]
  We propose a Single-Sentence Reader as a new approach for addressing answer position bias in MRC. Remarkably, in our experiments with six different models, our proposed Single-Sentence Readers trained on biased dataset achieve results that nearly match those of models trained on normal dataset.
  arXiv  Detail & Related papers  (2023-08-08T20:29:13Z)
• Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering [38.36299280464046]
  Extractive question answering (QA) models tend to exploit spurious correlations to make predictions. Relative position of an answer can be exploited by QA models as superficial cues for making predictions. We propose an ensemble-based debiasing method that does not require prior knowledge about the distribution of relative positions.
  arXiv  Detail & Related papers  (2022-10-26T08:01:38Z)
• The Curious Case of Absolute Position Embeddings [65.13827063579728]
  Transformer language models encode the notion of word order using positional information. In natural language, it is not absolute position that matters, but relative position, and the extent to which APEs can capture this type of information has not been investigated. We observe that models trained with APE over-rely on positional information to the point that they break-down when subjected to sentences with shifted position information.
  arXiv  Detail & Related papers  (2022-10-23T00:00:04Z)
• 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)
• Greedy Gradient Ensemble for Robust Visual Question Answering [163.65789778416172]
  We stress the language bias in Visual Question Answering (VQA) that comes from two aspects, i.e., distribution bias and shortcut bias. We propose a new de-bias framework, Greedy Gradient Ensemble (GGE), which combines multiple biased models for unbiased base model learning. GGE forces the biased models to over-fit the biased data distribution in priority, thus makes the base model pay more attention to examples that are hard to solve by biased models.
  arXiv  Detail & Related papers  (2021-07-27T08:02:49Z)

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.