arXiv Machine Learning
How Do Language Models Choose Between Context and Memory?
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
3d ago
To Copy or Not to Copy: Copying Is Easier to Induce Than Recall
arXiv:2601.12075v2 Announce Type: replace Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...
arXiv AI
Aug 5
Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models
arXiv:2601. 09445v2 Announce Type: replace-cross Abstract: In language models (LMs), intra-memory knowledge conflict arises when inconsistent information about the same subject is encoded within the model's parametric knowledge.
arXiv AI
Aug 24
Can LLMs Introspect? A Reality Check
The paper questions whether large language models (LLMs) truly introspect by critiquing recent studies that claim they can detect and report their internal states. It proposes two necessary conditions for genuine introspection: privileged access to internal representations and second‑order computation that distinguishes from first‑order task performance. Re‑examining two existing paradigms, the authors find that apparent introspective abilities can be explained by input‑based classifiers or generic anomaly detection, concluding that current evidence does not support metacognitive monitoring in LLMs.
arXiv Machine Learning
Jul 27
Learning What Matters: Supervising Sparse Attention Routing with Causal Evidence Sets
arXiv:2607. 21692v1 Announce Type: new Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input.
Hugging Face Trending Papers
Aug 14
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or s...
arXiv AI
Jun 12
Prefill Awareness in Large Language Models
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.