Academic
arXiv:2602.17691v1 Announce Type: cross Abstract: Quantized language models face a fundamental dilemma: low sampling temperatures yield repetitive, mode-collapsed outputs, while high temperatures (T > 2.0) …
arXiv:2602.17744v1 Announce Type: cross Abstract: We propose Bayesian optimal sequential prediction as a new principle for understanding in-context learning (ICL). Unlike interpretations framing Transformers as …
arXiv:2602.17837v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model …
arXiv:2602.17867v1 Announce Type: cross Abstract: Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature …
arXiv:2602.18008v1 Announce Type: cross Abstract: Mechanistic models encode scientific knowledge about dynamical systems and are widely used in downstream scientific and policy applications. Recent work …
arXiv:2602.18037v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language …
arXiv:2602.18297v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such …
arXiv:2602.18301v1 Announce Type: cross Abstract: Autoregressive large language models (LLMs) generate text token-by-token, requiring n forward passes to produce a sequence of length n. Recent …
arXiv:2602.18307v1 Announce Type: cross Abstract: Large language models have achieved striking results in interactive theorem proving, particularly in Lean. However, most benchmarks for LLM-based proof …
arXiv:2602.18333v1 Announce Type: cross Abstract: Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state …
arXiv:2602.18417v1 Announce Type: cross Abstract: This paper presents a direct framework for sequence models with hidden states on closed subgroups of U(d). We use a …
arXiv:2408.03099v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used for topic modeling, outperforming classical topic models such as LDA. Commonly, pre-trained LLM …
