arXiv AI
How Language Models Organize Task Information
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 16
Language Models Share a Readout Bottleneck in Working Memory
Large language models (LLMs) exhibit a human‑like working‑memory pattern on the N‑back task, with performance dropping as memory load increases and errors mainly on lure items. Two hypotheses—precision limits of softmax attention and interference from competing items—were tested across 15 pretrained LLMs and minimal transformers. Results show that interference, not precision, constrains LLMs’ working‑memory performance, as suppressing non‑target item identities improves sensitivity and larger models benefit more from reducing interference.
arXiv Computation and Language
Sep 25
Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax
The paper introduces a three-level evaluation framework—behavioral deployment, LM-head readout, and probe recoverability—to distinguish whether a language model fails a syntactic test by not encoding structure or by failing to use it. Using a trilingual control-dependency benchmark, the authors find that probe recoverability consistently exceeds LM-head readout, which in turn exceeds behavioral deployment across seven models and three languages, with the largest gap observed in Qwen3-0.6B Instruct. Layer-localized activation patching shows that instruction tuning shifts the decoded layer later, suggesting decoding favors surface shortcuts and that behavioral evaluation understates what models encode while probing alone overstates what they deploy.
arXiv AI
Oct 16
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
The paper investigates when a language model actually learns task information versus when its readout (unembedding matrix) learns to express that information. Using a new parameter‑trajectory cross‑coding method, the authors find that hidden states can encode task data early in training, but the readout reorganizes only in a narrow window (0.4–1.1% of Pythia’s pretraining). By varying the readout learning rate, they show that faster readout learning reduces the gap between hidden‑state encoding and output expression without affecting final performance.
arXiv Machine Learning
Aug 6
Unforgettable Generalization in Language Models
arXiv:2409. 02228v2 Announce Type: replace Abstract: When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change?
arXiv Machine Learning
Sep 16
Test-Time Unlearning via Sparse Autoencoder
arXiv:2609.16229v1 Announce Type: new Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify...
arXiv Machine Learning
Oct 16
Not All Change Is Damage: Update-Matched Unlearning for Large Language Models
The paper introduces Update‑Matched Unlearning (UMU), a method that applies the same simulated relearning update to both a defended model and an undefended reference to better preserve plasticity while resisting relearning of deleted knowledge. Experiments on Llama and Qwen models with TOFU and FaithUn datasets show that UMU reduces harmful and benign relearning by 30.4 and 9.9 points on average and increases new‑task accuracy by 3.5 points, supporting the reference‑timing hypothesis. The study demonstrates that robust unlearning should selectively prevent recovery of deleted knowledge without suppressing the model’s ability to learn new tasks.