# Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources

arXiv: https://arxiv.org/abs/2103.11320 · HTML: https://mlsanity.com/paper/2103.11320/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 54 references that are in the map.
- First posted on arXiv 21 Mar 2021.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [UnQovering Stereotyping Biases via Underspecified Questions](https://mlsanity.com/paper/2010.02428/) (2020)
- [A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation](https://mlsanity.com/paper/2001.05139/) (2020)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques](https://mlsanity.com/paper/1901.03116/) (2019)
- [Empath: Understanding Topic Signals in Large-Scale Text](https://mlsanity.com/paper/1602.06979/) (2016)
- [GenericsKB: A Knowledge Base of Generic Statements](https://mlsanity.com/paper/2005.00660/) (2020)
- [Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering](https://mlsanity.com/paper/2005.00691/) (2020)
- [Examining Gender Bias in Languages with Grammatical Gender](https://mlsanity.com/paper/1909.02224/) (2019)
- [R3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge](https://mlsanity.com/paper/2004.13248/) (2020)
- [Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition](https://mlsanity.com/paper/1910.10872/) (2019)
- [RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms](https://mlsanity.com/paper/2005.00782/) (2020)

## Built on by (most cited first, 30 of 30)

- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Deep Bidirectional Language-Knowledge Graph Pretraining](https://mlsanity.com/paper/2210.09338/) (2022)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge](https://mlsanity.com/paper/2305.08281/) (2023)
- [Perturbation Augmentation for Fairer NLP](https://mlsanity.com/paper/2205.12586/) (2022)
- [Graph Reasoning for Question Answering with Triplet Retrieval](https://mlsanity.com/paper/2305.18742/) (2023)
- [Commonsense-Focused Dialogues for Response Generation: An Empirical Study](https://mlsanity.com/paper/2109.06427/) (2021)
- [Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation](https://mlsanity.com/paper/2110.08501/) (2021)
- [Refined Commonsense Knowledge from Large-Scale Web Contents](https://mlsanity.com/paper/2112.04596/) (2021)
- [Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models](https://mlsanity.com/paper/2406.04064/) (2024)
- [Probing Commonsense Explanation in Dialogue Response Generation](https://mlsanity.com/paper/2104.09574/) (2021)
- [GD-COMET: A Geo-Diverse Commonsense Inference Model](https://mlsanity.com/paper/2310.15383/) (2023)
- [MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems](https://mlsanity.com/paper/2505.18943/) (2025)
- [PaCo: Preconditions Attributed to Commonsense Knowledge](https://mlsanity.com/paper/2104.08712/) (2021)
- [Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models](https://mlsanity.com/paper/2205.01841/) (2022)
- [KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding](https://mlsanity.com/paper/2210.04105/) (2022)
- [Towards Multi-Objective Statistically Fair Federated Learning](https://mlsanity.com/paper/2201.09917/) (2022)
- [Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation](https://mlsanity.com/paper/2205.09314/) (2022)
- [Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths](https://mlsanity.com/paper/2210.07621/) (2022)
- [Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks](https://mlsanity.com/paper/2305.08495/) (2023)
- ["Im not Racist but...": Discovering Bias in the Internal Knowledge of Large Language Models](https://mlsanity.com/paper/2310.08780/) (2023)
- [PInKS: Preconditioned Commonsense Inference with Minimal Supervision](https://mlsanity.com/paper/2206.07920/) (2022)
- [The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs](https://mlsanity.com/paper/2210.03353/) (2022)
- [The State of Profanity Obfuscation in Natural Language Processing](https://mlsanity.com/paper/2210.07595/) (2022)
- [Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction](https://mlsanity.com/paper/2410.12040/) (2024)
- [Do Children Texts Hold The Key To Commonsense Knowledge?](https://mlsanity.com/paper/2210.04530/) (2022)
- [On Degrees of Freedom in Defining and Testing Natural Language Understanding](https://mlsanity.com/paper/2305.15130/) (2023)
- [Preconditioned Visual Language Inference with Weak Supervision](https://mlsanity.com/paper/2306.01753/) (2023)
- [CASE: Commonsense-Augmented Score with an Expanded Answer Space](https://mlsanity.com/paper/2311.01684/) (2023)
- [Improving Commonsense Bias Classification by Mitigating the Influence of Demographic Terms](https://mlsanity.com/paper/2406.07229/) (2024)

## Abstract (arXiv)

Warning: this paper contains content that may be offensive or upsetting. Numerous natural language processing models have tried injecting commonsense by using the ConceptNet knowledge base to improve performance on different tasks. ConceptNet, however, is mostly crowdsourced from humans and may reflect human biases such as "lawyers are dishonest." It is important that these biases are not conflated with the notion of commonsense. We study this missing yet important problem by first defining and quantifying biases in ConceptNet as two types of representational harms: overgeneralization of polarized perceptions and representation disparity. We find that ConceptNet contains severe biases and disparities across four demographic categories. In addition, we analyze two downstream models that use ConceptNet as a source for commonsense knowledge and find the existence of biases in those models as well. We further propose a filtered-based bias-mitigation approach and examine its effectiveness. We show that our mitigation approach can reduce the issues in both resource and models but leads to a performance drop, leaving room for future work to build fairer and stronger commonsense models.