Oskar Van Der Wal

Also published as: Oskar van der Wal


2023

pdf
Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model
Abhijith Chintam | Rahel Beloch | Willem Zuidema | Michael Hanna | Oskar van der Wal
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP

Language models (LMs) exhibit and amplify many types of undesirable biases learned from the training data, including gender bias. However, we lack tools for effectively and efficiently changing this behavior without hurting general language modeling performance. In this paper, we study three methods for identifying causal relations between LM components and particular output: causal mediation analysis, automated circuit discovery and our novel, efficient method called DiffMask+ based on differential masking. We apply the methods to GPT-2 small and the problem of gender bias, and use the discovered sets of components to perform parameter-efficient fine-tuning for bias mitigation. Our results show significant overlap in the identified components (despite huge differences in the computational requirements of the methods) as well as success in mitigating gender bias, with less damage to general language modeling compared to full model fine-tuning. However, our work also underscores the difficulty of defining and measuring bias, and the sensitivity of causal discovery procedures to dataset choice. We hope our work can contribute to more attention for dataset development, and lead to more effective mitigation strategies for other types of bias.

pdf
Inseq: An Interpretability Toolkit for Sequence Generation Models
Gabriele Sarti | Nils Feldhus | Ludwig Sickert | Oskar van der Wal
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

Past work in natural language processing interpretability focused mainly on popular classification tasks while largely overlooking generation settings, partly due to a lack of dedicated tools. In this work, we introduce Inseq, a Python library to democratize access to interpretability analyses of sequence generation models. Inseq enables intuitive and optimized extraction of models’ internal information and feature importance scores for popular decoder-only and encoder-decoder Transformers architectures. We showcase its potential by adopting it to highlight gender biases in machine translation models and locate factual knowledge inside GPT-2. Thanks to its extensible interface supporting cutting-edge techniques such as contrastive feature attribution, Inseq can drive future advances in explainable natural language generation, centralizing good practices and enabling fair and reproducible model evaluations.

pdf
ChapGTP, ILLC’s Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation
Jaap Jumelet | Michael Hanna | Marianne de Heer Kloots | Anna Langedijk | Charlotte Pouw | Oskar van der Wal
Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning

2022

pdf
The Birth of Bias: A case study on the evolution of gender bias in an English language model
Oskar Van Der Wal | Jaap Jumelet | Katrin Schulz | Willem Zuidema
Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a relatively small language model, using the LSTM architecture trained on an English Wikipedia corpus. With full access to the data and to the model parameters as they change during every step while training, we can map in detail how the representation of gender develops, what patterns in the dataset drive this, and how the model’s internal state relates to the bias in a downstream task (semantic textual similarity).We find that the representation of gender is dynamic and identify different phases during training. Furthermore, we show that gender information is represented increasingly locally in the input embeddings of the model and that, as a consequence, debiasing these can be effective in reducing the downstream bias. Monitoring the training dynamics, allows us to detect an asymmetry in how the female and male gender are represented in the input embeddings. This is important, as it may cause naive mitigation strategies to introduce new undesirable biases. We discuss the relevance of the findings for mitigation strategies more generally and the prospects of generalizing our methods to larger language models, the Transformer architecture, other languages and other undesirable biases.

pdf
You reap what you sow: On the Challenges of Bias Evaluation Under Multilingual Settings
Zeerak Talat | Aurélie Névéol | Stella Biderman | Miruna Clinciu | Manan Dey | Shayne Longpre | Sasha Luccioni | Maraim Masoud | Margaret Mitchell | Dragomir Radev | Shanya Sharma | Arjun Subramonian | Jaesung Tae | Samson Tan | Deepak Tunuguntla | Oskar Van Der Wal
Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models

Evaluating bias, fairness, and social impact in monolingual language models is a difficult task. This challenge is further compounded when language modeling occurs in a multilingual context. Considering the implication of evaluation biases for large multilingual language models, we situate the discussion of bias evaluation within a wider context of social scientific research with computational work. We highlight three dimensions of developing multilingual bias evaluation frameworks: (1) increasing transparency through documentation, (2) expanding targets of bias beyond gender, and (3) addressing cultural differences that exist between languages. We further discuss the power dynamics and consequences of training large language models and recommend that researchers remain cognizant of the ramifications of developing such technologies.

2020

pdf
The Grammar of Emergent Languages
Oskar van der Wal | Silvan de Boer | Elia Bruni | Dieuwke Hupkes
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, we consider the syntactic properties of languages emerged in referential games, using unsupervised grammar induction (UGI) techniques originally designed to analyse natural language. We show that the considered UGI techniques are appropriate to analyse emergent languages and we then study if the languages that emerge in a typical referential game setup exhibit syntactic structure, and to what extent this depends on the maximum message length and number of symbols that the agents are allowed to use. Our experiments demonstrate that a certain message length and vocabulary size are required for structure to emerge, but they also illustrate that more sophisticated game scenarios are required to obtain syntactic properties more akin to those observed in human language. We argue that UGI techniques should be part of the standard toolkit for analysing emergent languages and release a comprehensive library to facilitate such analysis for future researchers.