Josef Valvoda

Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa et al. · eth-zurich, microsoft-research

The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements made on several fronts over the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 67 new languages, including 30 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g. missing gender and macron information. We have also amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet.

Niklas Stoehr, Lucas Torroba Hennigen, Josef Valvoda et al. · cambridge, eth-zurich

Measuring the intensity of events is crucial for monitoring and tracking armed conflict. Advances in automated event extraction have yielded massive data sets of "who did what to whom" micro-records that enable data-driven approaches to monitoring conflict. The Goldstein scale is a widely-used expert-based measure that scores events on a conflictual-cooperative scale. It is based only on the action category ("what") and disregards the subject ("who") and object ("to whom") of an event, as well as contextual information, like associated casualty count, that should contribute to the perception of an event's "intensity". This paper takes a latent variable-based approach to measuring conflict intensity. We introduce a probabilistic generative model that assumes each observed event is associated with a latent intensity class. A novel aspect of this model is that it imposes an ordering on the classes, such that higher-valued classes denote higher levels of intensity. The ordinal nature of the latent variable is induced from naturally ordered aspects of the data (e.g., casualty counts) where higher values naturally indicate higher intensity. We evaluate the proposed model both intrinsically and extrinsically, showing that it obtains comparatively good held-out predictive performance.

Josef Valvoda, Ryan Cotterell, Simone Teufel · cambridge

Every legal case sets a precedent by developing the law in one of the following two ways. It either expands its scope, in which case it sets positive precedent, or it narrows it, in which case it sets negative precedent. Legal outcome prediction, the prediction of positive outcome, is an increasingly popular task in AI. In contrast, we turn our focus to negative outcomes here, and introduce a new task of negative outcome prediction. We discover an asymmetry in existing models' ability to predict positive and negative outcomes. Where the state-of-the-art outcome prediction model we used predicts positive outcomes at 75.06 F1, it predicts negative outcomes at only 10.09 F1, worse than a random baseline. To address this performance gap, we develop two new models inspired by the dynamics of a court process. Our first model significantly improves positive outcome prediction score to 77.15 F1 and our second model more than doubles the negative outcome prediction performance to 24.01 F1. Despite this improvement, shifting focus to negative outcomes reveals that there is still much room for improvement for outcome prediction models.

Josef Valvoda, Naomi Saphra, Jonathan Rawski et al. · cambridge, cmu

Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large neural models in NLP can acquire this ability while learning from data is an open question. In this paper, we investigate this problem from the perspective of formal languages. We use deterministic finite-state transducers to make an unbounded number of datasets with controllable properties governing compositionality. By randomly sampling over many transducers, we explore which of their properties contribute to learnability of a compositional relation by a neural network. We find that the models either learn the relations completely or not at all. The key is transition coverage, setting a soft learnability limit at 400 examples per transition.

Tiago Pimentel, Josef Valvoda, Niklas Stoehr et al. · cambridge, eth-zurich

In this paper, we seek to measure how much information a component in a neural network could extract from the representations fed into it. Our work stands in contrast to prior probing work, most of which investigates how much information a model's representations contain. This shift in perspective leads us to propose a new principle for probing, the architectural bottleneck principle: In order to estimate how much information a given component could extract, a probe should look exactly like the component. Relying on this principle, we estimate how much syntactic information is available to transformers through our attentional probe, a probe that exactly resembles a transformer's self-attention head. Experimentally, we find that, in three models (BERT, ALBERT, and RoBERTa), a sentence's syntax tree is mostly extractable by our probe, suggesting these models have access to syntactic information while composing their contextual representations. Whether this information is actually used by these models, however, remains an open question.

Josef Valvoda, Yimai Fang, David Vandyke · cambridge

Dialog modelling faces a difficult trade-off. Models are trained on a large amount of text, yet their responses need to be limited to a desired scope and style of a dialog agent. Because the datasets used to achieve the former contain language that is not compatible with the latter, pre-trained dialog models are fine-tuned on smaller curated datasets. However, the fine-tuning process robs them of the ability to produce diverse responses, eventually reducing them to dull conversation partners. In this paper we investigate if prompting can mitigate the above trade-off. Specifically, we experiment with conditioning the prompt on the query, rather than training a single prompt for all queries. By following the intuition that freezing the pre-trained language model will conserve its expressivity, we find that compared to fine-tuning, prompting can achieve a higher BLEU score and substantially improve the diversity and novelty of the responses.

Alexandra Butoi, Ghazal Khalighinejad, Anej Svete et al. · allen-ai, cambridge

Characterizing the computational power of neural network architectures in terms of formal language theory remains a crucial line of research, as it describes lower and upper bounds on the reasoning capabilities of modern AI. However, when empirically testing these bounds, existing work often leaves a discrepancy between experiments and the formal claims they are meant to support. The problem is that formal language theory pertains specifically to recognizers: machines that receive a string as input and classify whether it belongs to a language. On the other hand, it is common instead to evaluate language models on proxy tasks, e.g., language modeling or sequence-to-sequence transduction, that are similar in only an informal sense to the underlying theory. We correct this mismatch by training and evaluating neural networks directly as binary classifiers of strings, using a general method that can be applied to a wide variety of languages. As part of this, we extend an algorithm recently proposed by Snæbjarnarson et al. (2025) for efficient length-controlled sampling of strings from regular languages. We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures: a simple RNN, an LSTM, and a causally-masked transformer. We find that the RNN and LSTM often outperform the transformer, and that auxiliary training objectives such as language modeling can help, although no single objective uniformly improves performance across languages and architectures. Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work. We have released our datasets as a benchmark called FLaRe (Formal Language Recognition), along with our code.

Josef Valvoda, Ryan Cotterell · cambridge

Current legal outcome prediction models - a staple of legal NLP - do not explain their reasoning. However, to employ these models in the real world, human legal actors need to be able to understand the model's decisions. In the case of common law, legal practitioners reason towards the outcome of a case by referring to past case law, known as precedent. We contend that precedent is, therefore, a natural way of facilitating explainability for legal NLP models. In this paper, we contribute a novel method for identifying the precedent employed by legal outcome prediction models. Furthermore, by developing a taxonomy of legal precedent, we are able to compare human judges and neural models with respect to the different types of precedent they rely on. We find that while the models learn to predict outcomes reasonably well, their use of precedent is unlike that of human judges.

Weijie Xu, Jay Desai, Fanyou Wu et al. · amazon-science, cambridge

Recent LLM (Large Language Models) advancements benefit many fields such as education and finance, but HR has hundreds of repetitive processes, such as access requests, medical claim filing and time-off submissions, which are unaddressed. We relate these tasks to the LLM agent, which has addressed tasks such as writing assisting and customer support. We present HR-Agent, an efficient, confidential, and HR-specific LLM-based task-oriented dialogue system tailored for automating repetitive HR processes such as medical claims and access requests. Since conversation data is not sent to an LLM during inference, it preserves confidentiality required in HR-related tasks.

Naaman Tan, Josef Valvoda, Tianyu Liu et al.

The relationship between the quality of a string, as judged by a human reader, and its probability, $p(\boldsymbol{y})$ under a language model undergirds the development of better language models. For example, many popular algorithms for sampling from a language model have been conceived with the goal of manipulating $p(\boldsymbol{y})$ to place higher probability on strings that humans deem of high quality. In this article, we examine the probability--quality relationship in language models explicitly aligned to human preferences, e.g., through reinforcement learning through human feedback. We show that, when sampling corpora from an aligned language model, there exists a trade-off between the strings' average reward and average log-likelihood under the prior language model, i.e., the same model before alignment with human preferences. We provide a formal treatment of this phenomenon and demonstrate how a choice of sampling adaptor allows for a selection of how much likelihood we exchange for the reward.

Nadav Borenstein, Anej Svete, Robin Chan et al.

What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of distributions over strings. While prior work in this direction focused on assessing the theoretical limits, in contrast, we seek to understand the empirical learnability. Unlike prior empirical work, we evaluate neural LMs on their home turf-learning probabilistic languages-rather than as classifiers of formal languages. In particular, we investigate the learnability of regular LMs (RLMs) by RNN and Transformer LMs. We empirically test the learnability of RLMs as a function of various complexity parameters of the RLM and the hidden state size of the neural LM. We find that the RLM rank, which corresponds to the size of linear space spanned by the logits of its conditional distributions, and the expected length of sampled strings are strong and significant predictors of learnability for both RNNs and Transformers. Several other predictors also reach significance, but with differing patterns between RNNs and Transformers.

Zeerak Talat, Hagen Blix, Josef Valvoda et al.

Ethics is one of the longest standing intellectual endeavors of humanity. In recent years, the fields of AI and NLP have attempted to wrangle with how learning systems that interact with humans should be constrained to behave ethically. One proposal in this vein is the construction of morality models that can take in arbitrary text and output a moral judgment about the situation described. In this work, we focus on a single case study of the recently proposed Delphi model and offer a critique of the project's proposed method of automating morality judgments. Through an audit of Delphi, we examine broader issues that would be applicable to any similar attempt. We conclude with a discussion of how machine ethics could usefully proceed, by focusing on current and near-future uses of technology, in a way that centers around transparency, democratic values, and allows for straightforward accountability.

Youmna Farag, Josef Valvoda, Helen Yannakoudakis et al.

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test model sensitivity to changes in syntax and semantics. We furthermore probe discourse embedding space and examine the knowledge that is encoded in representations of coherence. We hope this study shall provide further insight into how to frame the task and improve models of coherence assessment further. Finally, we make our datasets publicly available as a resource for researchers to use to test discourse coherence models.

Ekaterina Vylomova, Jennifer White, Elizabeth Salesky et al.

A broad goal in natural language processing (NLP) is to develop a system that has the capacity to process any natural language. Most systems, however, are developed using data from just one language such as English. The SIGMORPHON 2020 shared task on morphological reinflection aims to investigate systems' ability to generalize across typologically distinct languages, many of which are low resource. Systems were developed using data from 45 languages and just 5 language families, fine-tuned with data from an additional 45 languages and 10 language families (13 in total), and evaluated on all 90 languages. A total of 22 systems (19 neural) from 10 teams were submitted to the task. All four winning systems were neural (two monolingual transformers and two massively multilingual RNN-based models with gated attention). Most teams demonstrate utility of data hallucination and augmentation, ensembles, and multilingual training for low-resource languages. Non-neural learners and manually designed grammars showed competitive and even superior performance on some languages (such as Ingrian, Tajik, Tagalog, Zarma, Lingala), especially with very limited data. Some language families (Afro-Asiatic, Niger-Congo, Turkic) were relatively easy for most systems and achieved over 90% mean accuracy while others were more challenging.

Rowan Hall Maudslay, Josef Valvoda, Tiago Pimentel et al.

Measuring what linguistic information is encoded in neural models of language has become popular in NLP. Researchers approach this enterprise by training "probes" - supervised models designed to extract linguistic structure from another model's output. One such probe is the structural probe (Hewitt and Manning, 2019), designed to quantify the extent to which syntactic information is encoded in contextualised word representations. The structural probe has a novel design, unattested in the parsing literature, the precise benefit of which is not immediately obvious. To explore whether syntactic probes would do better to make use of existing techniques, we compare the structural probe to a more traditional parser with an identical lightweight parameterisation. The parser outperforms structural probe on UUAS in seven of nine analysed languages, often by a substantial amount (e.g. by 11.1 points in English). Under a second less common metric, however, there is the opposite trend - the structural probe outperforms the parser. This begs the question: which metric should we prefer?

Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay et al.

The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually ``know'' about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a linguistic task and trains a supervised model to predict annotations in that linguistic task from the network's learned representations. If the probe does well, the researcher may conclude that the representations encode knowledge related to the task. A commonly held belief is that using simpler models as probes is better; the logic is that simpler models will identify linguistic structure, but not learn the task itself. We propose an information-theoretic operationalization of probing as estimating mutual information that contradicts this received wisdom: one should always select the highest performing probe one can, even if it is more complex, since it will result in a tighter estimate, and thus reveal more of the linguistic information inherent in the representation. The experimental portion of our paper focuses on empirically estimating the mutual information between a linguistic property and BERT, comparing these estimates to several baselines. We evaluate on a set of ten typologically diverse languages often underrepresented in NLP research---plus English---totalling eleven languages.