This article provides a unified view of context-adaptive inference across three traditions that are usually treated separately: explicit adaptation in statistics, rapid task-specific adaptation in meta-learning and transfer, and implicit adaptation in large foundation models via prompting, retrieval, and expert routing.
Abstract
Modern predictive systems are expected to adapt their behavior to the specific situation they are facing. A clinical model should not treat every patient the same; a retrieval-augmented model should change its answer when given different evidence; a mixture-of-experts model should route different inputs to different experts. We call this capability context-adaptive inference: before predicting, the system uses information about the current context to specialize its parameters or computation for that instance. This article provides a unified view of context-adaptive inference across three traditions that are usually treated separately: (i) explicit adaptation in statistics (e.g. varying-coefficient models, local regression, hierarchical sharing), (ii) rapid task-specific adaptation in meta-learning and transfer, and (iii) implicit adaptation in large foundation models via prompting, retrieval, and expert routing. We formalize these approaches under a common objective: to map context $c$ to adapted parameters $\theta(c)$, then to predict via $f(x; \theta(c))$. Under squared loss, linear prediction heads, and fixed features, we prove that explicit parameter adaptation and implicit routing are mathematically equivalent to kernel ridge regression on joint features of inputs and context. Building on this bridge, we propose practical design principles and evaluation metrics including adaptation-efficiency, routing stability, and context-specific robustness to guide when to specialize, how to constrain that specialization, and how to audit context-adaptive models in deployment. Finally, we identify open problems in identifiability, robustness under distribution shift, and efficient large-scale adaptation, outlining design principles for methods that are scalable, reliable, and transparent in real-world settings.
A computational account of confidence in multimodal language models is provided, when answer logits behave as readouts of a latent decision variable is delineated, and statistical decision confidence is established as a unifying framework for studying confidence across biological and artificial intelligence.
D. Kumaran, Viorica Patraucean, M. Ovsjanikov et al.· 0 citations
In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causal language models trained by left-to-right autoregressive prediction, such as GPT-style models. Masked language models instead recover masked tokens from bidirectional context, and their role in ICL remains less understood. We develop a statistical learning framework that represents the context examples by their empirical measure and models prediction as a function of the context and the query. This formulation places autoregressive and masked pretraining objectives within a common excess-risk analysis. Under Wasserstein-type regularity conditions, we relate pretraining with T tasks and N samples per task to k-shot excess risk at inference, obtaining same-order upper bounds for masked and autoregressive objectives. We also study task-distribution shift, where pretraining tasks are sampled from P and inference tasks from Q; the resulting bound contains an additional term controlled by the lifted Wasserstein distance between P and Q. The bounds further imply an order-optimal allocation under a fixed pretraining data budget and refined rates under intrinsic low-dimensional structure. Experiments on controlled function-learning tasks show that the Masked Pair Encoder (MPE) can achieve performance comparable to GPT-2-style causal Transformers, suggesting that ICL behavior is not specific to causal language models.
Chenrui Liu, Chuanlong Xie, Falong Tan et al.· 0 citations
A hierarchical Bayesian framework for LLM reliability assessment is extended by relaxing the assumption of independent task outcomes and introducing a Hidden Markov Model to capture sequential dependence in benchmark-constructed interaction sessions, suggesting that ignoring sequential dependence may lead to overconfident reliability estimates.
Robab Aghazadeh Chakherlou, S. Khastgir, Peter Popov et al.· 0 citations
It is suggested that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates, and this gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs.
Patrik Wolf, Thomas Kleine Buening, Andreas Krause et al.· 0 citations
This work develops a six step BBN framework and illustrates it to model customer intention to consult a doctor in an alternative healthcare system and reveals that while self efficacy appears to be a major factor, its actual causal impact is small.
Kumar Rahul, Shovan Chowdhury Indian Institute of Management Kozhikode, Kerala et al.· 0 citations
Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data. However, such adaptation remains non-trivial: it often requires operationally challenging fine-tuning of open-source models or ad hoc prompt optimization. We study a minimal alternative based on a simple API-level control: allowing users to bias the model's logits with a user-defined vector. We develop a black-box method for learning a single context-independent logit-bias vector, added at every decoding step, without modifying model weights or requiring gradients. Starting from a KL-regularized reinforcement learning (RL) objective, we characterize when such a fixed logit-bias vector can approximate the optimal prefix-dependent correction and derive a closed-form inverse-propensity estimator from rollouts, rewards, and token probabilities. Empirically, this simple decoding-time intervention improves over base models on mathematical and reasoning benchmarks while using far fewer trainable parameters than conventional fine-tuning. Our results suggest that learned logit bias is a lightweight mechanism for adapting language models under minimal access requirements.
Ofek Cohen, Lior Shani, Aviv Rosenberg et al.· 0 citations
