arXiv:2605. 08934v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components.
By Ward Gauderis, Thomas Dooms, Steven T. Homer, Kola Ayonrinde, Geraint A. Wiggins
arXiv:2607. 18961v1 Announce Type: new Abstract: Large language models (LLMs) generate fluent text by incrementally predicting the next token from a prefix.
By Remo Pareschi
arXiv:2607. 25335v1 Announce Type: cross Abstract: Prompt compression shortens LLM input to reduce inference cost, yet existing methods score token importance through LM forward passes.
By Jianfei Ma, Zhaoxin Feng, Emmanuele Chersoni, Si Chen
arXiv:2603. 20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions.
By Christopher J. Agostino, Quan Le Thien, Nayan D'Souza, Louis van der Elst
Recent advancements in Large Language Models (LLMs) have enabled sophisticated reasoning and content generation, yet their inherent stochasticity poses significant challenges for ensuring predictive credibility. While traditional uncertainty taxonomy paradigms, such as the dichotomy of aleatoric and epistemic uncertainties, provide conceptual foundations, they often fail to capture the multi-component and multi-stage nature of LLM generation and struggle to evaluate the effectiveness of various Uncertainty Quantification (UQ) methods.
arXiv:2606. 30625v1 Announce Type: cross Abstract: Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosine similarity, effectively ignoring embedding magnitudes.
By Ziwei Su, Junyu Ren, Victor Veitch