Related papers: Darkness Visible: Reading the Exception Handler of…

Negation remains a persistent challenge for modern language models, often causing reversed meanings or factual errors. In this work, we conduct a causal analysis of how GPT-2 Small internally processes such linguistic transformations. We…

Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts spent on reinforcement learning from human feedback (RLHF),…

We consider the memorization capabilities of multilayered \emph{sign} perceptrons neural networks (SPNNs). A recent rigorous upper-bounding capacity characterization, obtained in \cite{Stojnictcmspnncaprdt23} utilizing the Random Duality…

Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnostic observer model detects hallucinations via a single…

Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on…

We present a novel and practical deep learning pipeline termed RandomForestMLP. This core trainable classification engine consists of a convolutional neural network backbone followed by an ensemble-based multi-layer perceptrons core for the…

Language models (LMs) like GPT-4 are important in AI applications, but their opaque decision-making process reduces user trust, especially in safety-critical areas. We introduce LMExplainer, a novel knowledge-grounded explainer that…

Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires…

In this paper, we make a contribution that can be understood from two perspectives: from an NLP perspective, we introduce a small challenge dataset for NLI with large lexical overlap, which minimises the possibility of models discerning…

Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel…

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite…

We introduce a proxy-analyzer framework for detecting hallucinations in large language models. Instead of looking inside the generating model, our system reads already-generated text through a small locally hosted open-weight model and…

We propose a novel neural network architecture, the normalized Transformer (nGPT) with representation learning on the hypersphere. In nGPT, all vectors forming the embeddings, MLP, attention matrices and hidden states are unit norm…

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

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…

Hallucination detection in Large Language Models (LLMs) is crucial for ensuring their reliability. This work presents our participation in the CLEF ELOQUENT HalluciGen shared task, where the goal is to develop evaluators for both generating…

Large language models (LLMs), such as GPT3.5, GPT4 and LLAMA2 perform surprisingly well and outperform human experts on many tasks. However, in many domain-specific evaluations, these LLMs often suffer from hallucination problems due to…

Fine-tuning pretrained language models has shown promising results on a wide range of tasks, but when encountering a novel task, do they rely more on generic pretrained representation, or develop brand new task-specific solutions? Here, we…

We propose the fully explainable Decision Tree Graph Neural Network (DT+GNN) architecture. In contrast to existing black-box GNNs and post-hoc explanation methods, the reasoning of DT+GNN can be inspected at every step. To achieve this, we…