Anna A. Ivanova

Kyle Mahowald, Anna A. Ivanova, Idan A. Blank et al.

Large Language Models (LLMs) have come closest among all models to date to mastering human language, yet opinions about their linguistic and cognitive capabilities remain split. Here, we evaluate LLMs using a distinction between formal linguistic competence -- knowledge of linguistic rules and patterns -- and functional linguistic competence -- understanding and using language in the world. We ground this distinction in human neuroscience, which has shown that formal and functional competence rely on different neural mechanisms. Although LLMs are surprisingly good at formal competence, their performance on functional competence tasks remains spotty and often requires specialized fine-tuning and/or coupling with external modules. We posit that models that use language in human-like ways would need to master both of these competence types, which, in turn, could require the emergence of mechanisms specialized for formal linguistic competence, distinct from functional competence.

Carina Kauf, Anna A. Ivanova, Giulia Rambelli et al.

Word co-occurrence patterns in language corpora contain a surprising amount of conceptual knowledge. Large language models (LLMs), trained to predict words in context, leverage these patterns to achieve impressive performance on diverse semantic tasks requiring world knowledge. An important but understudied question about LLMs' semantic abilities is whether they acquire generalized knowledge of common events. Here, we test whether five pre-trained LLMs (from 2018's BERT to 2023's MPT) assign higher likelihood to plausible descriptions of agent-patient interactions than to minimally different implausible versions of the same event. Using three curated sets of minimal sentence pairs (total n=1,215), we found that pre-trained LLMs possess substantial event knowledge, outperforming other distributional language models. In particular, they almost always assign higher likelihood to possible vs. impossible events (The teacher bought the laptop vs. The laptop bought the teacher). However, LLMs show less consistent preferences for likely vs. unlikely events (The nanny tutored the boy vs. The boy tutored the nanny). In follow-up analyses, we show that (i) LLM scores are driven by both plausibility and surface-level sentence features, (ii) LLM scores generalize well across syntactic variants (active vs. passive constructions) but less well across semantic variants (synonymous sentences), (iii) some LLM errors mirror human judgment ambiguity, and (iv) sentence plausibility serves as an organizing dimension in internal LLM representations. Overall, our results show that important aspects of event knowledge naturally emerge from distributional linguistic patterns, but also highlight a gap between representations of possible/impossible and likely/unlikely events.

Kamya Hari, Taha Binhuraib, Jin Li et al.

Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise, inter-subject variability, and redundancy arising from spatially correlated voxels encoding overlapping neural signals. Here, we propose an independent component (IC)-based encoding framework that dissociates stimulus-driven and noise-driven signals in fMRI data. We decompose continuous fMRI data from naturalistic story listening into ICs using one subset of the data, and train encoding models on independent data to predict IC time series from large language model representations of linguistic input. Across subjects, a subset of ICs exhibited consistently high predictivity. These ICs were spatially and temporally consistent across subjects and included cognitive networks known to respond during story listening (auditory and language). Auditory component time series were strongly correlated with acoustic stimulus features, highlighting the interpretability of identified component time series. Components identified as noise or motion-related artifacts by ICA-AROMA showed uniformly poor predictive performance, confirming that highly predicted components reflect genuine stimulus-related neural signals rather than confounds. Overall, IC-based encoding models enable analyses at the level of functional networks, accommodating the variability in network locations across individuals and providing interpretable results that are easy to compare across subjects.

Taha Binhuraib, Ruimin Gao, Anna A. Ivanova

We introduce LITcoder, an open-source library for building and benchmarking neural encoding models. Designed as a flexible backend, LITcoder provides standardized tools for aligning continuous stimuli (e.g., text and speech) with brain data, transforming stimuli into representational features, mapping those features onto brain data, and evaluating the predictive performance of the resulting model on held-out data. The library implements a modular pipeline covering a wide array of methodological design choices, so researchers can easily compose, compare, and extend encoding models without reinventing core infrastructure. Such choices include brain datasets, brain regions, stimulus feature (both neural-net-based and control, such as word rate), downsampling approaches, and many others. In addition, the library provides built-in logging, plotting, and seamless integration with experiment tracking platforms such as Weights & Biases (W&B). We demonstrate the scalability and versatility of our framework by fitting a range of encoding models to three story listening datasets: LeBel et al. (2023), Narratives, and Little Prince. We also explore the methodological choices critical for building encoding models for continuous fMRI data, illustrating the importance of accounting for all tokens in a TR scan (as opposed to just taking the last one, even when contextualized), incorporating hemodynamic lag effects, using train-test splits that minimize information leakage, and accounting for head motion effects on encoding model predictivity. Overall, LITcoder lowers technical barriers to encoding model implementation, facilitates systematic comparisons across models and datasets, fosters methodological rigor, and accelerates the development of high-quality high-performance predictive models of brain activity. Project page: https://litcoder-brain.github.io

Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin et al. · ibm-research, mit

The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- especially those based on language models -- has proven challenging, in large part because of the difficulty of disentangling conceptual knowledge about the world from knowledge of surface co-occurrence statistics. This paper presents Elements of World Knowledge (EWoK), a framework for evaluating language models' understanding of the conceptual knowledge underlying world modeling. EWoK targets specific concepts from multiple knowledge domains known to be important for world modeling in humans, from social interactions (help, deceive) to spatial relations (left, right). Objects, agents, and locations in the items can be flexibly filled in, enabling easy generation of multiple controlled datasets. We then introduce EWoK-core-1.0, a dataset of 4,374 items covering 11 world knowledge domains. We evaluate 20 open-weights large language models (1.3B--70B parameters) and compare them with human performance. All tested models perform worse than humans, with results varying drastically across domains. Performance on social interactions and social properties was highest and performance on physical relations and spatial relations was lowest. Overall, this dataset highlights simple cases where even large models struggle and presents rich avenues for targeted research on LLM world modeling capabilities.

Carina Kauf, Emmanuele Chersoni, Alessandro Lenci et al.

Semantic plausibility (e.g. knowing that "the actor won the award" is more likely than "the actor won the battle") serves as an effective proxy for general world knowledge. Language models (LMs) capture vast amounts of world knowledge by learning distributional patterns in text, accessible via log probabilities (LogProbs) they assign to plausible vs. implausible outputs. The new generation of instruction-tuned LMs can now also provide explicit estimates of plausibility via prompting. Here, we evaluate the effectiveness of LogProbs and basic prompting to measure semantic plausibility, both in single-sentence minimal pairs (Experiment 1) and short context-dependent scenarios (Experiment 2). We find that (i) in both base and instruction-tuned LMs, LogProbs offers a more reliable measure of semantic plausibility than direct zero-shot prompting, which yields inconsistent and often poor results; (ii) instruction-tuning generally does not alter the sensitivity of LogProbs to semantic plausibility (although sometimes decreases it); (iii) across models, context mostly modulates LogProbs in expected ways, as measured by three novel metrics of context-sensitive plausibility and their match to explicit human plausibility judgments. We conclude that, even in the era of prompt-based evaluations, LogProbs constitute a useful metric of semantic plausibility, both in base and instruction-tuned LMs.

Om Bhatt, Anna A. Ivanova

Language models (LMs) are known to be prone to response biases, which present as option preference biases in fixed-response questions. It is therefore imperative to develop low-cost and effective response bias correction methods to improve LM performance and enable more accurate evaluations of model abilities. Here, we propose a simple response bias correction strategy ($\texttt{RBCorr}$) and test it on 12 open-weight language models using yes-no, entailment, and multiple choice questions. We show that response bias is prevalent in LMs pre-correction and that $\texttt{RBCorr}$ effectively eliminates bias and boosts model performance. We also explore the generalizability of bias behavior across models, datasets, and prompt formats, showing that LogProbs-based correction is highly dependent on all three of these aspects. Overall, $\texttt{RBCorr}$ is an easy-to-use method that can boost the performance of smaller LMs and ensure that LM performance on closed-response benchmarks aligns more closely with their true capabilities.

Anna A. Ivanova

Language models have become an essential part of the burgeoning field of AI Psychology. I discuss 14 methodological considerations that can help design more robust, generalizable studies evaluating the cognitive abilities of language-based AI systems, as well as to accurately interpret the results of these studies.

Anna A. Ivanova, John Hewitt, Noga Zaslavsky

A major challenge in both neuroscience and machine learning is the development of useful tools for understanding complex information processing systems. One such tool is probes, i.e., supervised models that relate features of interest to activation patterns arising in biological or artificial neural networks. Neuroscience has paved the way in using such models through numerous studies conducted in recent decades. In this work, we draw insights from neuroscience to help guide probing research in machine learning. We highlight two important design choices for probes $-$ direction and expressivity $-$ and relate these choices to research goals. We argue that specific research goals play a paramount role when designing a probe and encourage future probing studies to be explicit in stating these goals.