arXiv Machine Learning
Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 21
The First Drop of Ink: Nonlinear Impact of Distracting Information in Long-Context Reasoning
arXiv:2605. 10828v2 Announce Type: replace Abstract: As large language models are increasingly deployed in retrieval-augmented generation and agentic systems that accumulate extensive context, understanding how distracting information affects long-context performance becomes critical.
arXiv AI
Aug 13
Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge
arXiv:2608. 12218v1 Announce Type: cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories.
arXiv AI
Sep 3
Language Models Can Control Their Own Attention
The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.
arXiv AI
Jul 3
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
arXiv:2607. 02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications.
arXiv AI
Sep 1
MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects
MUDDLE is a benchmark designed to disentangle the effects of document length and topical distractors on document question‑answering systems. It contains 270 human‑annotated questions, each tested in five conditions: the source alone, the source with two or four hard negatives (topically similar), and the source with two or four random distractors matched in length and provenance. Experiments with GPT‑5‑mini show that hard negatives reduce accuracy more than length‑matched random distractors, indicating that topical similarity is a more significant source of error than length alone.
Hugging Face Trending Papers
Jul 2
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization.