Robust Pronoun Use Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?

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 components at a time. To measure progress towards the combined goal, we introduce the task of pronoun use fidelity: given a context introducing a co-referring entity and pronoun, the task is to reuse the correct pronoun later, independent of potential distractors. We present a carefully-designed dataset of over 5 million instances to evaluate pronoun use fidelity in English, and we use it to evaluate 37 popular large language models across architectures (encoder-only, decoder-only and encoder-decoder) and scales (11M-70B parameters). We find that while models can mostly faithfully reuse previously-specified pronouns in the presence of no distractors, they are significantly worse at processing she/her/her, singular they and neopronouns. Additionally, models are not robustly faithful to pronouns, as they are easily distracted. With even one additional sentence containing a distractor pronoun, accuracy drops on average by 34%. With 5 distractor sentences, accuracy drops by 52% for decoder-only models and 13% for encoder-only models. We show that widely-used large language models are still brittle, with large gaps in reasoning and in processing different pronouns in a setting that is very simple for humans, and we encourage researchers in bias and reasoning to bridge them.

Argument Quality Assessment in the Age of Instruction-Following Large Language Models

The computational treatment of arguments on controversial issues has been subject to extensive NLP research, due to its envisioned impact on opinion formation, decision making, writing education, and the like. A critical task in any such application is the assessment of an argument's quality - but it is also particularly challenging. In this position paper, we start from a brief survey of argument quality research, where we identify the diversity of quality notions and the subjectiveness of their perception as the main hurdles towards substantial progress on argument quality assessment. We argue that the capabilities of instruction-following large language models (LLMs) to leverage knowledge across contexts enable a much more reliable assessment. Rather than just fine-tuning LLMs towards leaderboard chasing on assessment tasks, they need to be instructed systematically with argumentation theories and scenarios as well as with ways to solve argument-related problems. We discuss the real-world opportunities and ethical issues emerging thereby.

Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ

Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small handful of high-resource languages (e.g. Mixtral, Qwen). Recent research shows that, despite limits in their intended use, people prompt LLMs in many different languages. Therefore, in this paper, we investigate the basic multilingual capabilities of state-of-the-art open LLMs beyond their intended use. For this purpose, we introduce MultiQ, a new silver standard benchmark for basic open-ended question answering with 27.4k test questions across a typologically diverse set of 137 languages. With MultiQ, we evaluate language fidelity, i.e.\ whether models respond in the prompted language, and question answering accuracy. All LLMs we test respond faithfully and/or accurately for at least some languages beyond their intended use. Most models are more accurate when they respond faithfully. However, differences across models are large, and there is a long tail of languages where models are neither accurate nor faithful. We explore differences in tokenization as a potential explanation for our findings, identifying possible correlations that warrant further investigation.

What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing and adapting different types of knowledge, e.g., in dedicated modularized structures, and on how to effectively combine these, e.g., by learning additional parameters. However, given the many possible options, a thorough understanding of the mechanisms involved in these compositions is missing, and hence it remains unclear which strategies to utilize. To address this research gap, we propose a novel framework for zero-shot module composition, which encompasses existing and some novel variations for selecting, weighting, and combining parameter modules under a single unified notion. Focusing on the scenario of domain knowledge and adapter layers, our framework provides a systematic unification of concepts, allowing us to conduct the first comprehensive benchmarking study of various zero-shot knowledge composition strategies. In particular, we test two module combination methods and five selection and weighting strategies for their effectiveness and efficiency in an extensive experimental setup. Our results highlight the efficacy of ensembling but also hint at the power of simple though often-ignored weighting methods. Further in-depth analyses allow us to understand the role of weighting vs. top-k selection, and show that, to a certain extent, the performance of adapter composition can even be predicted.

Exploring Jiu-Jitsu Argumentation for Writing Peer Review Rebuttals

In many domains of argumentation, people's arguments are driven by so-called attitude roots, i.e., underlying beliefs and world views, and their corresponding attitude themes. Given the strength of these latent drivers of arguments, recent work in psychology suggests that instead of directly countering surface-level reasoning (e.g., falsifying given premises), one should follow an argumentation style inspired by the Jiu-Jitsu 'soft' combat system (Hornsey and Fielding, 2017): first, identify an arguer's attitude roots and themes, and then choose a prototypical rebuttal that is aligned with those drivers instead of invalidating those. In this work, we are the first to explore Jiu-Jitsu argumentation for peer review by proposing the novel task of attitude and theme-guided rebuttal generation. To this end, we enrich an existing dataset for discourse structure in peer reviews with attitude roots, attitude themes, and canonical rebuttals. To facilitate this process, we recast established annotation concepts from the domain of peer reviews (e.g., aspects a review sentence is relating to) and train domain-specific models. We then propose strong rebuttal generation strategies, which we benchmark on our novel dataset for the task of end-to-end attitude and theme-guided rebuttal generation and two subtasks.

A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation

Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethical considerations behind. In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. Concretely, we compute established gender bias metrics on the WinoMT corpus from English to German and Spanish. We discover that IFT models default to male-inflected translations, even disregarding female occupational stereotypes. Next, using interpretability methods, we unveil that models systematically overlook the pronoun indicating the gender of a target occupation in misgendered translations. Finally, based on this finding, we propose an easy-to-implement and effective bias mitigation solution based on few-shot learning that leads to significantly fairer translations.

Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research

With language technology increasingly affecting individuals' lives, many recent works have investigated the ethical aspects of NLP. Among other topics, researchers focused on the notion of morality, investigating, for example, which moral judgements language models make. However, there has been little to no discussion of the terminology and the theories underpinning those efforts and their implications. This lack is highly problematic, as it hides the works' underlying assumptions and hinders a thorough and targeted scientific debate of morality in NLP. In this work, we address this research gap by (a) providing an overview of some important ethical concepts stemming from philosophy and (b) systematically surveying the existing literature on moral NLP w.r.t. their philosophical foundation, terminology, and data basis. For instance, we analyse what ethical theory an approach is based on, how this decision is justified, and what implications it entails. Our findings surveying 92 papers show that, for instance, most papers neither provide a clear definition of the terms they use nor adhere to definitions from philosophy. Finally, (c) we give three recommendations for future research in the field. We hope our work will lead to a more informed, careful, and sound discussion of morality in language technology.

ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale

Multi-task learning (MTL) has shown considerable practical benefits, particularly when using pre-trained language models (PLMs). While this is commonly achieved by simultaneously learning $n$ tasks under a joint optimization procedure, recent methods such as AdapterFusion structure the problem into two distinct stages: (i) task learning, where knowledge specific to a task is encapsulated within sets of parameters (\eg adapters), and (ii) transfer, where this already learned knowledge is leveraged for a target task. This separation of concerns provides numerous benefits, such as promoting reusability, and addressing cases involving data privacy and societal concerns; on the flip side, current two-stage MTL methods come with the cost of introducing a substantial number of additional parameters. In this work, we address this issue by leveraging the usefulness of linearly scaling the output representations of source adapters for transfer learning. We introduce ScaLearn, a simple and highly parameter-efficient two-stage MTL method that capitalizes on the knowledge of the source tasks by learning a minimal set of scaling parameters that enable effective knowledge transfer to a target task. Our experiments on three benchmarks (GLUE, SuperGLUE, and HumSet) show that our ScaLearn, in addition to facilitating the benefits of two-stage MTL, consistently outperforms strong baselines with only a small number of transfer parameters - roughly 0.35% of those of AdapterFusion. Remarkably, we observe that ScaLearn maintains its strong abilities even when further reducing parameters through uniform scaling and layer-sharing, achieving similarly competitive results with only $8$ transfer parameters for each target task. Our proposed approach thus demonstrates the power of simple scaling as a promise for more efficient task transfer.

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

Generating bitmap graphics from text has gained considerable attention, yet for scientific figures, vector graphics are often preferred. Given that vector graphics are typically encoded using low-level graphics primitives, generating them directly is difficult. To address this, we propose the use of TikZ, a well-known abstract graphics language that can be compiled to vector graphics, as an intermediate representation of scientific figures. TikZ offers human-oriented, high-level commands, thereby facilitating conditional language modeling with any large language model. To this end, we introduce DaTikZ the first large-scale TikZ dataset, consisting of 120k TikZ drawings aligned with captions. We fine-tune LLaMA on DaTikZ, as well as our new model CLiMA, which augments LLaMA with multimodal CLIP embeddings. In both human and automatic evaluation, CLiMA and LLaMA outperform commercial GPT-4 and Claude 2 in terms of similarity to human-created figures, with CLiMA additionally improving text-image alignment. Our detailed analysis shows that all models generalize well and are not susceptible to memorization. GPT-4 and Claude 2, however, tend to generate more simplistic figures compared to both humans and our models. We make our framework, AutomaTikZ, along with model weights and datasets, publicly available.