← Back to all news
arXiv Machine Learning By Leon Chlon, Julie Huang

When Thoughts Become Memory: Unifying In-Context Learning and Fine-Tuning

Read the original on arXiv Machine Learning →

The paper presents a certified rule that determines whether unseen data should be incorporated into a pretrained model’s context or its weights, based on an exact law for their information value. This law quantifies the code length saved on held‑out queries as the expected bits stored about the query, adjusted by a prior repair and decoding loss, and applies to any model, architecture, dataset, or task. The authors demonstrate that the rule’s ceilings correctly certify choices across diverse models—including transformers, TabPFN, occupancy networks, and stereo networks—and that an anytime‑valid test can reliably select the better approach (e.g., TabPFN over XGBoost or GPT‑2’s cache over fine‑tuning) with controlled error rates.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computer Vision
Aug 24

When does fusing hand-crafted knowledge with learned representations pay? A cost-normalized benchmark of stacking, substitution, and interference

arXiv:2608.21098v1 Announce Type: new Abstract: Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or har...

By Ahmad AlMughrabi, Albert Clop, Benjamin Busam, Ricardo Marques, Petia Radeva
computer-visionbenchmarks
More like this →
arXiv Machine Learning
Oct 8

When Should an In-Context Learner Expand Its Hypothesis Space?

The paper investigates when an in‑context learner should expand its hypothesis space, framing the decision as a costly sequential problem where prediction failures must be translated into structural evidence and then into an action. Using a Structural Revision Environment that allows exact Bayesian analysis, the authors find that the optimal decision to expand is governed by a value boundary rather than a simple evidence threshold, and that this boundary depends on the price of expansion, the remaining horizon, and the specific predictions that cannot be repaired locally. Experiments with transformers and language models show that while these models exhibit a failure‑sensitive signal, they often fail to incorporate cost and horizon considerations into their expansion decisions, and post‑training adjustments to priors or prediction sharpness do not alter the expansion criterion.

By Weihan Li, Xinlei Chen, Junhao Wu, Tianshi Zheng
llms
More like this →
arXiv Computation and Language
4d ago

Better Retrievers, Worse Labels: How Incomplete Relevance Judgments Distort Abstention Evaluation in Conversational RAG

The paper investigates how conversational Retrieval-Augmented Generation (RAG) benchmarks that rely on relevance judgments to determine context sufficiency can be misleading. By re‑running official baselines on the RETECO track and evaluating with both large‑language‑model judges and a blind audit, the authors show that stronger retrievers produce a higher proportion of contexts lacking gold documents yet still containing the answer, leading to a sharp drop in shortcut precision from 0.68 to 0.10. The study demonstrates that many false misses arise from hard negatives, gold content from other turns, or neighboring chunks, and that using retrieval scores alone as a sufficiency detector can underestimate answerability by up to 0.19 in AUROC.

By Ivan Kochergin, Vasily Konovalov
llmsragbenchmarks
More like this →