Language Models (LMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax. In this paper, we argue that causal interpretability methods, applied to LMs, can greatly enhance the value of such evidence by helping us characterize the abstract mechanisms that LMs learn to use. Our empirical focus is a set of English filler-gap dependency constructions (e.g., questions, relative clauses). Linguistic theories largely agree that these constructions share many properties. Using experiments based in Distributed Interchange Interventions, we show that LMs converge on similar abstract analyses of these constructions. These analyses also reveal previously overlooked factors -- relating to frequency, filler type, and surrounding context -- that could motivate changes to standard linguistic theory. Overall, these results suggest that mechanistic, internal analyses of LMs can push linguistic theory forward.

The cognitive essence of humans is deeply intertwined with the concept of animacy, which plays an essential role in shaping their memory, vision, and multi-layered language understanding. Although animacy appears in language via nuanced constraints on verbs and adjectives, it is also learned and refined through extralinguistic information. Similarly, we assume that the LLMs' limited abilities to understand natural language when processing animacy are motivated by the fact that these models are trained exclusively on text. Hence, the question this paper aims to answer arises: can LLMs, in their digital wisdom, process animacy in a similar way to what humans would do? We then propose a systematic analysis via prompting approaches. In particular, we probe different LLMs by prompting them using animate, inanimate, usual, and stranger contexts. Results reveal that, although LLMs have been trained predominantly on textual data, they exhibit human-like behavior when faced with typical animate and inanimate entities in alignment with earlier studies. Hence, LLMs can adapt to understand unconventional situations by recognizing oddities as animated without needing to interface with unspoken cognitive triggers humans rely on to break down animations.

Neural network language models (LMs) have been shown to successfully capture complex linguistic knowledge. However, their utility for understanding language acquisition is still debated. We contribute to this debate by presenting a case study where we use LMs as simulated learners to derive novel experimental hypotheses to be tested with humans. We apply this paradigm to study cross-dative generalization (CDG): productive generalization of novel verbs across dative constructions (she pilked me the ball/she pilked the ball to me) -- acquisition of which is known to involve a large space of contextual features -- using LMs trained on child-directed speech. We specifically ask: "what properties of the training exposure facilitate a novel verb's generalization to the (unmodeled) alternate construction?" To answer this, we systematically vary the exposure context in which a novel dative verb occurs in terms of the properties of the theme and recipient, and then analyze the LMs' usage of the novel verb in the unmodeled dative construction. We find LMs to replicate known patterns of children's CDG, as a precondition to exploring novel hypotheses. Subsequent simulations reveal a nuanced role of the features of the novel verbs' exposure context on the LMs' CDG. We find CDG to be facilitated when the first postverbal argument of the exposure context is pronominal, definite, short, and conforms to the prototypical animacy expectations of the exposure dative. These patterns are characteristic of harmonic alignment in datives, where the argument with features ranking higher on the discourse prominence scale tends to precede the other. This gives rise to a novel hypothesis that CDG is facilitated insofar as the features of the exposure context -- in particular, its first postverbal argument -- are harmonically aligned. We conclude by proposing future experiments that can test this hypothesis in children.

Animacy - whether an entity is alive and sentient - is fundamental to cognitive processing, impacting areas such as memory, vision, and language. However, animacy is not always expressed directly in language: in English it often manifests indirectly, in the form of selectional constraints on verbs and adjectives. This poses a potential issue for transformer language models (LMs): they often train only on text, and thus lack access to extralinguistic information from which humans learn about animacy. We ask: how does this impact LMs' animacy processing - do they still behave as humans do? We answer this question using open-source LMs. Like previous studies, we find that LMs behave much like humans when presented with entities whose animacy is typical. However, we also show that even when presented with stories about atypically animate entities, such as a peanut in love, LMs adapt: they treat these entities as animate, though they do not adapt as well as humans. Even when the context indicating atypical animacy is very short, LMs pick up on subtle clues and change their behavior. We conclude that despite the limited signal through which LMs can learn about animacy, they are indeed sensitive to the relevant lexical semantic nuances available in English.

Grammatical cues are sometimes redundant with word meanings in natural language. For instance, English word order rules constrain the word order of a sentence like "The dog chewed the bone" even though the status of "dog" as subject and "bone" as object can be inferred from world knowledge and plausibility. Quantifying how often this redundancy occurs, and how the level of redundancy varies across typologically diverse languages, can shed light on the function and evolution of grammar. To that end, we performed a behavioral experiment in English and Russian and a cross-linguistic computational analysis measuring the redundancy of grammatical cues in transitive clauses extracted from corpus text. English and Russian speakers (n=484) were presented with subjects, verbs, and objects (in random order and with morphological markings removed) extracted from naturally occurring sentences and were asked to identify which noun is the subject of the action. Accuracy was high in both languages (~89% in English, ~87% in Russian). Next, we trained a neural network machine classifier on a similar task: predicting which nominal in a subject-verb-object triad is the subject. Across 30 languages from eight language families, performance was consistently high: a median accuracy of 87%, comparable to the accuracy observed in the human experiments. The conclusion is that grammatical cues such as word order are necessary to convey subjecthood and objecthood in a minority of naturally occurring transitive clauses; nevertheless, they can (a) provide an important source of redundancy and (b) are crucial for conveying intended meaning that cannot be inferred from the words alone, including descriptions of human interactions, where roles are often reversible (e.g., Ray helped Lu/Lu helped Ray), and expressing non-prototypical meanings (e.g., "The bone chewed the dog.").

The social applications of robots possess intrinsic challenges with respect to social paradigms and heterogeneity of different groups. These challenges can be in the form of social acceptability, anthropomorphism, likeability, past experiences with robots etc. In this paper, we have considered a group of neurotypical adults to describe how different voices and motion types of the NAO robot can have effect on the perceived safety, anthropomorphism, likeability, animacy, and perceived intelligence of the robot. In addition, prior robot experience has also been taken into consideration to perform this analysis using a one-way Analysis of Variance (ANOVA). Further, we also demonstrate that these different modalities instigate different physiological responses in the person. This classification has been done using two different deep learning approaches, 1) Convolutional Neural Network (CNN), and 2) Gramian Angular Fields on the Blood Volume Pulse (BVP) data recorded. Both of these approaches achieve better than chance accuracy 25% for a 4 class classification.

A personification is a figure of speech that endows inanimate entities with properties and actions typically seen as requiring animacy. In this paper, we explore the task of personification generation. To this end, we propose PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation. We curate a corpus of personifications called PersonifCorp, together with automatically generated de-personified literalizations of these personifications. We demonstrate the usefulness of this parallel corpus by training a seq2seq model to personify a given literal input. Both automatic and human evaluations show that fine-tuning with PersonifCorp leads to significant gains in personification-related qualities such as animacy and interestingness. A detailed qualitative analysis also highlights key strengths and imperfections of PINEAPPLE over baselines, demonstrating a strong ability to generate diverse and creative personifications that enhance the overall appeal of a sentence.

Animacy is the characteristic of being able to independently carry out actions in a story world (e.g., movement, communication). It is a necessary property of characters in stories, and so detecting animacy is an important step in automatic story understanding. Prior approaches to animacy detection have conceived of animacy as a word- or phrase-level property, without explicitly connecting it to characters. In this work we compute the animacy of referring expressions using a statistical approach incorporating features such as word embeddings on referring expression, noun, grammatical subject and semantic roles. We then compute the animacy of coreference chains via a majority vote of the animacy of the chain's constituent referring expressions.

Creativity in social robots requires further attention in the interdisciplinary field of Human-Robot Interaction (HRI). This paper investigates the hypothesised connection between the perceived creative agency and the animacy of social robots. The goal of this work is to assess the relevance of robot movements in the attribution of creativity to robots. The results of this work inform the design of future Human-Robot Creative Interactions (HRCI). The study uses a storytelling game based on visual imagery inspired by the game 'Story Cubes' to explore the perceived creative agency of social robots. This game is used to tell a classic story for children with an alternative ending. A 2x2 experiment was designed to compare two conditions: the robot telling the original version of the story and the robot plot-twisting the end of the story. A Robotis Mini humanoid robot was used for the experiment. As a novel contribution, we propose an adaptation of the Short Scale Creative Self scale (SSCS) to measure perceived creative agency in robots. We also use the Godspeed scale to explore different attributes of social robots in this setting. We did not obtain significant main effects of the robot movements or the story in the participants' scores. However, we identified significant main effects of the robot movements in features of animacy, likeability, and perceived safety. This initial work encourages further studies experimenting with different robot embodiment and movements to evaluate the perceived creative agency in robots and inform the design of future robots that participate in creative interactions.

Although models using contextual word embeddings have achieved state-of-the-art results on a host of NLP tasks, little is known about exactly what information these embeddings encode about the context words that they are understood to reflect. To address this question, we introduce a suite of probing tasks that enable fine-grained testing of contextual embeddings for encoding of information about surrounding words. We apply these tasks to examine the popular BERT, ELMo and GPT contextual encoders, and find that each of our tested information types is indeed encoded as contextual information across tokens, often with near-perfect recoverability-but the encoders vary in which features they distribute to which tokens, how nuanced their distributions are, and how robust the encoding of each feature is to distance. We discuss implications of these results for how different types of models breakdown and prioritize word-level context information when constructing token embeddings.