20 accepted papers
Interpreting the internal process of neural models has long been a challenge. This challenge remains relevant in the era of large language models (LLMs) and in-context learning (ICL); for example, ICL poses a new issue of interpreting which example in the few-shot examples contributed to identifying…
This study evaluates Large Language Models’ (LLMs) ability to simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (L1). In dialogue-based interviews, we prompt LLMs to mimic L2 English learners with specific L1s (e.g., J…
Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective. One fundamental question is why this human–LM gap arises. This study explores the advantage of grounded language acquisition, specifically the impact of visual information — which human…
As large language models (LLMs) continue to evolve, leaderboards play a significant role in steering their development. Existing leaderboards often prioritize model capabilities while overlooking safety concerns, leaving a significant gap in responsible AI development. To address this gap, we introd…
Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of features learned by, e.g., sparse auto-encoders (SAEs), is evaluated. This paradigm naturally raises a critical question:…
Whether language models (LMs) have inductive biases that favor typologically frequent grammatical properties over rare, implausible ones has been investigated, typically using artificial languages (ALs) (White and Cotterell, 2021; Kuribayashi et al., 2024). In this paper, we extend these works from
Transformers are ubiquitous in wide tasks. Interpreting their internals is a pivotal goal. Nevertheless, their particular components, feed-forward (FF) blocks, have typically been less analyzed despite their substantial parameter amounts. We analyze the input contextualization effects of FF blocks…
Visual Question Answering~(VQA) is an important task in multimodal AI, which requires models to understand and reason on knowledge present in visual and textual data. However, most of the current VQA datasets and models are primarily focused on English and a few major world languages, with images th…
The world’s languages exhibit certain so-called typological or implicational universals; for example, Subject-Object-Verb (SOV) languages typically use postpositions. Explaining the source of such biases is a key goal of linguistics.We study word-order universals through a computational simulation w…
Explicit multi-step reasoning, such as chain-of-thought, is widely adopted in the community to explore the better performance of language models (LMs). We report on the systematic strategy that LMs use in this process.Our controlled experiments reveal that LMs rely more heavily on heuristics, such a…
Instruction tuning aligns the response of large language models (LLMs) with human preferences.Despite such efforts in human–LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling perspective. More specifically, next-word probabilities estimated…
Speakers sometimes omit certain arguments of a predicate in a sentence; such omission is especially frequent in pro-drop languages. This study addresses a question about ellipsis—what can explain the native speakers’ ellipsis decisions?—motivated by the interest in human discourse processing and wri…
Large language models (LLMs) take advantage of step-by-step reasoning instructions, e.g., chain-of-thought (CoT) prompting. Building on this, their ability to perform CoT-style reasoning robustly is of interest from a probing perspective. In this study, we inspect the step-by-step reasoning abilit…
With the success of neural language models (LMs), their language acquisition has gained much attention. This work sheds light on the second language (L2) acquisition of LMs, while previous work has typically explored their first language (L1) acquisition. Specifically, we trained bilingual LMs with…
Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, this component has often been overlooked in analyzing Transformers.In this study, we investigate the inner workings of the prediction head, specifically focusing on bias parameters. Our ex…
Language models (LMs) have been used in cognitive modeling as well as engineering studies—they compute information-theoretic complexity metrics that simulate humans’ cognitive load during reading.This study highlights a limitation of modern neural LMs as the model of choice for this purpose: there i…
Humans use different wordings depending on the context to facilitate efficient communication. For example, instead of completely new information, information related to the preceding context is typically placed at the sentence-initial position. In this study, we analyze whether neural language model…
Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only composed of the multi-head attention; other components can al…
In computational psycholinguistics, various language models have been evaluated against human reading behavior (e.g., eye movement) to build human-like computational models. However, most previous efforts have focused almost exclusively on English, despite the recent trend towards linguistic univers…
Events in a narrative differ in salience: some are more important to the story than others. Estimating event salience is useful for tasks such as story generation, and as a tool for text analysis in narratology and folkloristics. To compute event salience without any annotations, we adopt Barthes’ d…