The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task
Not on the map. Why?
Abstract (arXiv)
A writer's style depends not just on personal traits but also on her intent and mental state. In this paper, we show how variants of the same writing task can lead to measurable differences in writing style. We present a case study based on the story cloze task (Mostafazadeh et al., 2016a), where annotators were assigned similar writing tasks with different constraints: (1) writing an entire story, (2) adding a story ending for a given story context, and (3) adding an incoherent ending to a story. We show that a simple linear classifier informed by stylistic features is able to successfully distinguish among the three cases, without even looking at the story context. In addition, combining our stylistic features with language model predictions reaches state of the art performance on the story cloze challenge. Our results demonstrate that different task framings can dramatically affect the way people write.
Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Feb 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 16; 2022: 8; 2023: 9; 2024: 4; 2025: 1; 2026: 1.
39 papers.
Sort:
By area:
- 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
- 2023Large Language Models are not Fair Evaluatorscited by 1,050
- 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
- 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
- 2024Are We Done with MMLU?cited by 178
- 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 68
- 2022Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasetscited by 54
- 2022Don't Blame the Annotator: Bias Already Starts in the Annotation Instructionscited by 47
- 2021It's not Rocket Science : Interpreting Figurative Language in Narrativescited by 39
- 2021Perceptual Score: What Data Modalities Does Your Model Perceive?cited by 35
- 2021Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistantscited by 31
27 more
- 2022Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal Viewcited by 31
- 2021Automatic Story Generation: Challenges and Attemptscited by 28
- 2023It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performancecited by 25
- 2021LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generationcited by 24
- 2021Avoiding Inference Heuristics in Few-shot Prompt-based Finetuningcited by 23
- 2021Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understandingcited by 19
- 2022On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlationscited by 19
- 2021Is Everything in Order? A Simple Way to Order Sentencescited by 15
- 2021Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classificationcited by 8
- 2021Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifierscited by 5
- 2021A Temporal Variational Model for Story Generationcited by 5
- 2023Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biasescited by 5
- 2023InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Modelscited by 5
- 2022A Proposal to Study "Is High Quality Data All We Need?"cited by 2
- 2023From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoningcited by 2
- 2024OffensiveLang: A Community Based Implicit Offensive Language Datasetcited by 2
- 2021Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmarkcited by 1
- 2022A Survey of Parameters Associated with the Quality of Benchmarks in NLPcited by 1
- 2023Beyond Turing: A Comparative Analysis of Approaches for Detecting Machine-Generated Textcited by 1
- 2024Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialoguescited by 1
- 2025Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inferencecited by 1
- 2026Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Studycited by 1
- 2021Problems and Countermeasures in Natural Language Processing Evaluationcited by 0
- 2022How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasetscited by 0
- 2023Real-Time Visual Feedback to Guide Benchmark Creation: A Human-and-Metric-in-the-Loop Workflowcited by 0
- 2023LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversitycited by 0
- 2024Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inferencecited by 0
- 2026Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study14 Apr 2026
- 2025Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference6 Mar 2025
- 2024Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference11 Oct 2024
- 2024Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues4 Oct 2024
- 2024Are We Done with MMLU?6 Jun 2024
- 2024OffensiveLang: A Community Based Implicit Offensive Language Dataset4 Mar 2024
- 2023InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models21 Dec 2023
- 2023Beyond Turing: A Comparative Analysis of Approaches for Detecting Machine-Generated Text21 Nov 2023
- 2023From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning24 Oct 2023
- 2023Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases30 May 2023
- 2023Large Language Models are not Fair Evaluators29 May 2023
- 2023It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance15 May 2023
27 more
- 2023LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity12 Apr 2023
- 2023Real-Time Visual Feedback to Guide Benchmark Creation: A Human-and-Metric-in-the-Loop Workflow9 Feb 2023
- 2023Prompting for Multimodal Hateful Meme Classification8 Feb 2023
- 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs24 Oct 2022
- 2022A Survey of Parameters Associated with the Quality of Benchmarks in NLP14 Oct 2022
- 2022Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions1 May 2022
- 2022On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations27 Apr 2022
- 2022Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets24 Mar 2022
- 2022Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View23 Mar 2022
- 2022A Proposal to Study "Is High Quality Data All We Need?"12 Mar 2022
- 2022How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets12 Jan 2022
- 2021Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants16 Dec 2021
- 2021Perceptual Score: What Data Modalities Does Your Model Perceive?27 Oct 2021
- 2021Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark22 Oct 2021
- 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Models14 Oct 2021
- 2021A Temporal Variational Model for Story Generation14 Sep 2021
- 2021Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding10 Sep 2021
- 2021Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers10 Sep 2021
- 2021Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning9 Sep 2021
- 2021It's not Rocket Science : Interpreting Figurative Language in Narratives31 Aug 2021
- 2021LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation30 Aug 2021
- 2021Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification29 Aug 2021
- 2021Problems and Countermeasures in Natural Language Processing Evaluation20 Apr 2021
- 2021Is Everything in Order? A Simple Way to Order Sentences14 Apr 2021
- 2021Automatic Story Generation: Challenges and Attempts25 Feb 2021
- 2021Calibrate Before Use: Improving Few-Shot Performance of Language Models19 Feb 2021
- 2021Challenges in Automated Debiasing for Toxic Language Detection29 Jan 2021
- 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
- 2023Large Language Models are not Fair Evaluatorscited by 1,050
- 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
- 2024Are We Done with MMLU?cited by 178
- 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 68
- 2022Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasetscited by 54
- 2022Don't Blame the Annotator: Bias Already Starts in the Annotation Instructionscited by 47
- 2021It's not Rocket Science : Interpreting Figurative Language in Narrativescited by 39
- 2021Perceptual Score: What Data Modalities Does Your Model Perceive?cited by 35
- 2021Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistantscited by 31
- 2022Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal Viewcited by 31
12 most cited of 36 All 36 (JSON)
- 2026Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study14 Apr 2026
- 2025Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference6 Mar 2025
- 2024Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference11 Oct 2024
- 2024Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues4 Oct 2024
- 2024Are We Done with MMLU?6 Jun 2024
- 2024OffensiveLang: A Community Based Implicit Offensive Language Dataset4 Mar 2024
- 2023InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models21 Dec 2023
- 2023Beyond Turing: A Comparative Analysis of Approaches for Detecting Machine-Generated Text21 Nov 2023
- 2023Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases30 May 2023
- 2023Large Language Models are not Fair Evaluators29 May 2023
- 2023It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance15 May 2023
- 2023LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity12 Apr 2023
12 newest of 36 All 36 (JSON)