# Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias

arXiv: https://arxiv.org/abs/2305.16409 · HTML: https://mlsanity.com/paper/2305.16409/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 13 of 13)

- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [Gender-preserving Debiasing for Pre-trained Word Embeddings](https://mlsanity.com/paper/1906.00742/) (2019)
- [Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction](https://mlsanity.com/paper/2105.06965/) (2021)
- [Kernelized Concept Erasure](https://mlsanity.com/paper/2201.12191/) (2022)
- [Detecting Perceived Emotions in Hurricane Disasters](https://mlsanity.com/paper/2004.14299/) (2020)
- [Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces](https://mlsanity.com/paper/2010.02976/) (2020)
- [How people talk about each other: Modeling Generalized Intergroup Bias and Emotion](https://mlsanity.com/paper/2209.06687/) (2022)

## Built on by (most cited first, 2 of 2)

- [ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions](https://mlsanity.com/paper/2407.02472/) (2024)
- [Language Models Predict Empathy Gaps Between Social In-groups and Out-groups](https://mlsanity.com/paper/2503.01030/) (2025)

## Abstract (arXiv)

While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this paper, we investigate if two pragmatic features (specificity and affect) systematically vary in different intergroup contexts -- thus connecting this new framing of bias to language output. Preliminary analysis finds modest correlations between specificity and affect of tweets with supervised intergroup relationship (IGR) labels. Counterfactual probing further reveals that while neural models finetuned for predicting IGR labels reliably use affect in classification, the model's usage of specificity is inconclusive. Code and data can be found at: https://github.com/venkatasg/intergroup-probing