We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (internals). Using this framework, we examine over 20 OLMo, Llama, and Mistral models, bridging behavioral and internal perspectives for toxicity for the first time. Our results show that LMs strongly encode information about the toxicity level of inputs and subsequent outputs, particularly in lower layers. Focusing on how unique LMs differ offers both correlative and causal evidence that they generate less toxic output when strongly encoding information about the input toxicity. We also highlight the heterogeneity of toxicity, as model behavior and internals vary across unique attributes such as Threat. Finally, four case studies analyzing detoxification, multi-prompt evaluations, model quantization, and pre-training dynamics underline the practical impact of aligned probing with further concrete insights. Our findings contribute to a more holistic understanding of LMs, both within and beyond the context of toxicity.

Personal names simultaneously differentiate individuals and categorize them in ways that are important in a given society. While the natural language processing community has thus associated personal names with sociodemographic characteristics in a variety of tasks, researchers have engaged to varying degrees with the established methodological problems in doing so. To guide future work that uses names and sociodemographic characteristics, we provide an overview of relevant research: first, we present an interdisciplinary background on names and naming. We then survey the issues inherent to associating names with sociodemographic attributes, covering problems of validity (e.g., systematic error, construct validity), as well as ethical concerns (e.g., harms, differential impact, cultural insensitivity). Finally, we provide guiding questions along with normative recommendations to avoid validity and ethical pitfalls when dealing with names and sociodemographic characteristics in natural language processing.

Interpretability and analysis (IA) research is a growing subfield within NLP with the goal of developing a deeper understanding of the behavior or inner workings of NLP systems and methods. Despite growing interest in the subfield, a commonly voiced criticism is that it lacks actionable insights and therefore has little impact on NLP. In this paper, we seek to quantify the impact of IA research on the broader field of NLP. We approach this with a mixed-methods analysis of: (1) a citation graph of 185K+ papers built from all papers published at ACL and EMNLP conferences from 2018 to 2023, and (2) a survey of 138 members of the NLP community. Our quantitative results show that IA work is well-cited outside of IA, and central in the NLP citation graph. Through qualitative analysis of survey responses and manual annotation of 556 papers, we find that NLP researchers build on findings from IA work and perceive it is important for progress in NLP, multiple subfields, and rely on its findings and terminology for their own work. Many novel methods are proposed based on IA findings and highly influenced by them, but highly influential non-IA work cites IA findings without being driven by them. We end by summarizing what is missing in IA work today and provide a call to action, to pave the way for a more impactful future of IA research.

Recent improvements in natural language processing (NLP) and machine learning (ML) and increased mainstream adoption have led to researchers frequently discussing the "democratization" of artificial intelligence. In this paper, we seek to clarify how democratization is understood in NLP and ML publications, through large-scale mixed-methods analyses of papers using the keyword "democra*" published in NLP and adjacent venues. We find that democratization is most frequently used to convey (ease of) access to or use of technologies, without meaningfully engaging with theories of democratization, while research using other invocations of "democra*" tends to be grounded in theories of deliberation and debate. Based on our findings, we call for researchers to enrich their use of the term democratization with appropriate theory, towards democratic technologies beyond superficial access.

In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without needing any parameter updates. Although there have been extensive studies on English in-context learning, multilingual in-context learning remains under-explored, and we lack an in-depth understanding of the role of demonstrations in this context. To address this gap, we conduct a multidimensional analysis of multilingual in-context learning, experimenting with 5 models from different model families, 9 datasets covering classification and generation tasks, and 56 typologically diverse languages. Our results reveal that the effectiveness of demonstrations varies significantly across models, tasks, and languages. We also find that strong instruction-following models including Llama 2-Chat, GPT-3.5, and GPT-4 are largely insensitive to the quality of demonstrations. Instead, a carefully crafted template often eliminates the benefits of demonstrations for some tasks and languages altogether. These findings show that the importance of demonstrations might be overestimated. Our work highlights the need for granular evaluation across multiple axes towards a better understanding of in-context learning.

Robust, faithful and harm-free pronoun use for individuals is an important goal for language models as their use increases, but prior work tends to study only one or two of these characteristics at a time. To measure progress towards the combined goal, we introduce the task of pronoun fidelity: given a context introducing a co-referring entity and pronoun, the task is to reuse the correct pronoun later. We present RUFF, a carefully-designed dataset of over 5 million instances to measure robust pronoun fidelity in English, and we evaluate 37 popular large language models across architectures (encoder-only, decoder-only and encoder-decoder) and scales (11M-70B parameters). When an individual is introduced with a pronoun, models can mostly faithfully reuse this pronoun in the next sentence, but they are significantly worse with she/her/her, singular they and neopronouns. Moreover, models are easily distracted by non-adversarial sentences discussing other people; even one additional sentence with a distractor pronoun causes accuracy to drop on average by 34%. Our results show that pronoun fidelity is neither robust, nor due to reasoning, in a simple, naturalistic setting where humans achieve nearly 100% accuracy. We encourage researchers to bridge the gaps we find and to carefully evaluate reasoning in settings where superficial repetition might inflate perceptions of model performance.

ORCA (Shen et al., 2023) is a recent technique for cross-modal fine-tuning, i.e., applying pre-trained transformer models to modalities beyond their training data. The technique consists primarily of training an embedder and fine-tuning the embedder and model. Despite its high performance on a variety of downstream tasks, we do not understand precisely how each of these components contribute to ORCA's success. Therefore, we run a series of ablations and find that embedder training does not help 2D tasks at all, contrary to what the original paper posits. In 1D tasks, some amount of embedder training is necessary but more is not better. In 4 out of 6 datasets we experiment with, it is model fine-tuning that makes the biggest difference. Through our ablations and baselines, we contribute a better understanding of the individual components of ORCA.

If a question cannot be answered with the available information, robust systems for question answering (QA) should know _not_ to answer. One way to build QA models that do this is with additional training data comprised of unanswerable questions, created either by employing annotators or through automated methods for unanswerable question generation. To show that the model complexity of existing automated approaches is not justified, we examine a simpler data augmentation method for unanswerable question generation in English: performing antonym and entity swaps on answerable questions. Compared to the prior state-of-the-art, data generated with our training-free and lightweight strategy results in better models (+1.6 F1 points on SQuAD 2.0 data with BERT-large), and has higher human-judged relatedness and readability. We quantify the raw benefits of our approach compared to no augmentation across multiple encoder models, using different amounts of generated data, and also on TydiQA-MinSpan data (+9.3 F1 points with BERT-large). Our results establish swaps as a simple but strong baseline for future work.

These notions vary across conceptualization Intersectionality is a critical framework that, through inquiry and (e.g., group, individual fairness [8]) and operationalization (e.g., praxis, allows us to examine how social inequalities persist through pre/in/post-processing [2]) [54]; nevertheless, the literature generally domains of structure and discipline. Given AI fairness' raison d'être agrees on the goal of minimizing negative outcomes across of "fairness," we argue that adopting intersectionality as an analytical demographic groups, including groups associated with multiple, framework is pivotal to effectively operationalizing fairness. "intersectional" demographic attributes (e.g., Black women) [92]. Through a critical review of how intersectionality is discussed in However, Kong [66] observes that AI fairness papers often narrowly 30 papers from the AI fairness literature, we deductively and inductively: interpret intersectional subgroup fairness as intersectionality, the 1) map how intersectionality tenets operate within the critical framework from which the term originates [29, 67]. This AI fairness paradigm and 2) uncover gaps between the conceptualization myopic conceptualization of intersectionality has non-trivial consequences and operationalization of intersectionality. We find that for just AI design and epistemology (i.e., ways of knowing).