The paper identifies a single direction in the unembedding matrix of large language models that encodes the unigram distribution of the training corpus, acting as a Bayesian prior when the model is uncertain. By projecting the final prediction state onto this direction, the authors derive a per‑token prior loading factor, λ, which decreases as context becomes more informative and decomposes predictions into a tempered prior and a context‑driven likelihood. Experiments across four model families (Llama, Qwen, Gemma, Pythia) show that larger models rely less on the prior in high‑context settings and that manipulating λ can steer predictions toward or away from the unigram prior in KL divergence.
arXiv:2506.17871v4 Announce Type: replace-cross Abstract: Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this cons...
The paper investigates how the structural entanglement of facts within a large language model’s knowledge base influences whether those facts leak after unlearning. Using two unlearning algorithms (WHP and GA+KL) across fictional and real-world datasets and multiple model sizes, the authors find that highly entangled facts are more likely to be recalled before unlearning, but the relationship changes—WHP weakens it while GA+KL reverses it. By directly manipulating entanglement scores and observing corresponding recall changes, they demonstrate a causal link and develop a predictive tool to audit prompts for potential leakage.
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:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on t...
arXiv:2606. 15877v1 Announce Type: cross Abstract: Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning.
arXiv:2607. 18422v1 Announce Type: new Abstract: Overparameterized models often have continuous parameter symmetries, so different parameters define the same predictor.
Large Language Bayes (LLB) samples probabilistic programs from a language model, runs approximate inference on each, and averages them weighted by an exponentiated evidence bound. The authors demonstrate that this weighting is not invariant to reparameterisation, unlike the log marginal likelihood, leading to significant discrepancies in weights across different program formulations. These discrepancies can reach up to 31.9×, affect Bayes factors, and introduce controlled errors in posterior estimates.
arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.
The paper presents a mean‑field analysis of attention in language models, defining an average attention kernel that propagates representations layer by layer. When conditioned on a whole corpus, the kernel predicts the average evolution of representation geometry; when conditioned on a single context, it predicts the expected geometry for that context. The difference between actual attention and the mean‑field prediction—called the mean‑field deviation—captures context‑specific computation, revealing how models diverge from average behavior during training and in few‑shot tasks.
arXiv:2610.00910v1 Announce Type: cross Abstract: Human reasoning depends on how objects are related within propositions. \textit{How do relations organize the language representations of contextual...
arXiv:2507. 11768v3 Announce Type: replace-cross Abstract: Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-preserving order, yet transformers change next-token probabilities when the same examples are serialized differently.
arXiv:2606. 30850v1 Announce Type: new Abstract: Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environment.