REVIEW 6 cited by
In-Context Learning with Long-Context Models: An In-Depth Exploration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
As model context lengths continue to increase, the number of demonstrations that can be provided in-context approaches the size of entire training datasets. We study the behavior of in-context learning (ICL) at this extreme scale on multiple datasets and models. We show that, for many datasets with large label spaces, performance continues to increase with thousands of demonstrations. We contrast this with example retrieval and finetuning: example retrieval shows excellent performance at low context lengths but has diminished gains with more demonstrations; finetuning is more data hungry than ICL but can exceed long-context ICL performance with additional data. We use the ICL setting to study several properties of both in-context learning and long-context models. We show that long-context ICL is less sensitive to random input shuffling than short-context ICL, that grouping of same-label examples negatively impacts performance, and that the performance boosts do not arise from cumulative gain from encoding many examples together. We conclude that long-context ICL can be an effective tool, and may not require long-context for encoding the demonstration set at all.
Forward citations
Cited by 6 Pith papers
-
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods ...
-
Towards Compute-Optimal Many-Shot In-Context Learning
Hybrid demonstration selection that adds 20 similar examples to a large cached random or k-means set matches or beats similarity-only selection at up to 10x lower estimated inference cost in many-shot ICL.
-
LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework
LOOM-Scope is a framework that standardizes long-context LLM evaluation across 22 benchmarks and integrates a lightweight 12-benchmark suite, LOOMBench, for fast comprehensive assessment.
-
An Auditable Agent Platform For Automated Molecular Optimisation
A hierarchical multi-agent LLM platform with recorded provenance improved average predicted binding affinity for AKT1 by 31%, while single-agent runs favored drug-likeness.
-
Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis
For Flamingo-style models, increasing the number of in-context examples improves language coherence but degrades visual-text alignment, and similarity-based image retrieval inflates CIDEr scores by encouraging caption...
-
Refract ICL: Rethinking Example Selection in the Era of Million-Token Models
In long-context models, more demonstrations do not automatically help; repeating hard examples and appending the model's own zero-shot predictions gives small, inconsistent gains.
Discussion (0). Sign in to comment.