相关论文: Garden-Path Traversal in GPT-2

Large transformer-based language models dominate modern NLP, yet our understanding of how they encode linguistic information relies primarily on studies of early models like BERT and GPT-2. We systematically probe 25 models from BERT Base…

We show new results about the garden-hose model. Our main results include improved lower bounds based on non-deterministic communication complexity (leading to the previously unknown $\Theta(n)$ bounds for Inner Product mod 2 and…

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

Explainability and interpretability are two important concepts, the absence of which can and should impede the application of well-performing neural networks to real-world problems. At the same time, they are difficult to incorporate into…

Large language models are increasingly used as writing tools and pedagogical resources in English for Academic Purposes, but it remains unclear whether they encode culturally differentiated representations when generating academic text.…

When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less is…

While graph neural networks (GNNs) have shown a great potential in various tasks on graph, the lack of transparency has hindered understanding how GNNs arrived at its predictions. Although few explainers for GNNs are explored, the…

We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens. Treating the hidden-state trajectory as a flow on an implicit Riemannian manifold, we analyze the layerwise…

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate,…

Given a sequence of tokens, such as words, the task of next-token prediction is to predict the next-token conditional probability distribution. Decoder-only transformers have become effective models for this task, but their properties are…

Modern task-oriented semantic parsing approaches typically use seq2seq transformers to map textual utterances to semantic frames comprised of intents and slots. While these models are empirically strong, their specific strengths and…

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…

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and successful approach to such tasks whenever the two sets of…

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

Autoregressive Language Models (LLMs) trained on Next-Token Prediction (NTP) often suffer from Topic Drift where the generation wanders away from the initial prompt due to a reliance on local associations rather than global planning. While…

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Use of large language models such as ChatGPT (GPT-4/GPT-5) for mental health support has grown rapidly, emerging as a promising route to assess and help people with mood disorders like depression. However, we have a limited understanding of…

Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought. We investigate this capability using GPT2-style language models trained from scratch on controlled…