相关论文: Identifying a Circuit for Verb Conjugation in GPT-…

In-Context Learning (ICL) is an intriguing ability of large language models (LLMs). Despite a substantial amount of work on its behavioral aspects and how it emerges in miniature setups, it remains unclear which mechanism assembles task…

In recent years, robots are used in an increasing variety of tasks, especially by small- and medium- sized enterprises. These tasks are usually fast-changing, they have a collaborative scenario and happen in unpredictable environments with…

Transformer-based language models (LMs) can perform a wide range of tasks, and mechanistic interpretability (MI) aims to reverse engineer the components responsible for task completion to understand their behavior. Previous MI research has…

Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from…

While instruction-tuned models have shown remarkable success in various natural language processing tasks, accurately evaluating their ability to follow instructions remains challenging. Existing benchmarks primarily focus on common…

Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models. Existing automated circuit discovery work applies activation…

Transformer-based language models achieve high performance on various tasks, but we still lack understanding of the kind of linguistic knowledge they learn and rely on. We evaluate three models (BERT, RoBERTa, and ALBERT), testing their…

One of the most powerful and enduring ideas in written discourse analysis is that genres can be described in terms of the moves which structure a writer's purpose. Considerable research has sought to identify these distinct communicative…

Language models such as GPT-2 have performed well on constructing syntactically sound sentences for text auto-completion task. However, such models often require considerable training effort to adapt to specific writing domains (e.g.,…

Transformer-based language models are treated as black-boxes because of their large number of parameters and complex internal interactions, which is a serious safety concern. Mechanistic Interpretability (MI) intends to reverse-engineer…

Sentence matching is a fundamental task of natural language processing with various applications. Most recent approaches adopt attention-based neural models to build word- or phrase-level alignment between two sentences. However, these…

Subject-verb agreement in the presence of an attractor noun located between the main noun and the verb elicits complex behavior: judgments of grammaticality are modulated by the grammatical features of the attractor. For example, in the…

As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training…

Compositional generalization-the systematic combination of known components into novel structures-remains a core challenge in cognitive science and machine learning. Although transformer-based large language models can exhibit strong…

We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems…

Argumentative structure prediction aims to establish links between textual units and label the relationship between them, forming a structured representation for a given input text. The former task, linking, has been identified by earlier…

Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue. Previous research in open-domain dialogue generation has…

Recent work has shown that computation in language models may be human-understandable, with successful efforts to localize and intervene on both single-unit features and input-output circuits. Here, we introduce an approach which extends…

Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling. In this paper, we…

The paper explores how video models trained for classification tasks represent nuanced, hidden semantic information that may not affect the final outcome, a key challenge for Trustworthy AI models. Through Explainable and Interpretable AI…