arXiv:2605.08143v1 Announce Type: new Abstract: Large language models encode vast factual knowledge that inevitably becomes outdated or incorrect after deployment, yet retraining is costly prohibitive, motivating model editing in lifelong settings that updates targeted behavior without harming the rest of…
arXiv:2605.09838v1 Announce Type: cross Abstract: Sentiment analysis has been of long-standing interest in psychotherapy research. Recently, the Transformer deep learning architecture has produced text-based sentiment analysis models that are highly accurate and context-aware. These models have been explored as proxies…
arXiv:2605.08144v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge this assumption and introduce NoiseRater, a…
arXiv:2605.10241v1 Announce Type: cross Abstract: Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increase the coverage of diverse utterances. In this study, we report the construction of a…
arXiv:2605.08149v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) decompose large language model representations into interpretable features, but how these features interact under uncertainty remains poorly understood. We introduce Feature Rivalry — negatively correlated SAE feature pairs — and study whether…
arXiv:2605.10795v1 Announce Type: cross Abstract: Large language models demonstrate remarkable ability in factual recall, yet the fundamental limits of storing and retrieving input–output associations with neural networks remain unclear. We study these limits in a minimal setting: a linear associative…
arXiv:2605.08150v1 Announce Type: new Abstract: We present a PyTorch package that compiles neural networks and their weights from Turing machine descriptions, producing models that exactly simulate the specified machine without any training. Given a transition function and a set of…
arXiv:2504.10766v2 Announce Type: replace Abstract: As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how different data affect finetuning dynamics remains largely unexplored. In this paper, we present a spectral analysis of layer-wise…
arXiv:2605.08153v1 Announce Type: new Abstract: With the rapid development of machine learning applications on time-series data, accurately assessing the value of training samples has become essential for data selection, noise detection, and model optimization. However, traditional data valuation methods usually…
arXiv:2605.08416v1 Announce Type: cross Abstract: Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a fundamental structure. These seemingly distant fields both seek to predict…
