Pith. sign in

REVIEW 13 cited by

Effective Long-Context Scaling of Foundation Models

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

arxiv 2309.16039 v3 pith:AKQW2IBS submitted 2023-09-27 cs.CL

classification cs.CL
keywords longlong-contextpretrainingtaskscontexteffectivellamabenchmarks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts are upsampled. We perform extensive evaluation on language modeling, synthetic context probing tasks, and a wide range of research benchmarks. On research benchmarks, our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2. Notably, with a cost-effective instruction tuning procedure that does not require human-annotated long instruction data, the 70B variant can already surpass gpt-3.5-turbo-16k's overall performance on a suite of long-context tasks. Alongside these results, we provide an in-depth analysis on the individual components of our method. We delve into Llama's position encodings and discuss its limitation in modeling long dependencies. We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

    cs.CL 2025-07 unverdicted novelty 6.0 of 10

    MemAgent uses multi-conversation RL to train a memory agent that reads text in segments and overwrites memory, extrapolating from 8K training to 3.5M token QA with under 5% loss and 95%+ on 512K RULER.

  2. From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ProxyReward trains long-form generation models by rewarding how well an AI judge can answer generated yes/no questions about the response, improving open-source models on ProxyQA.

  3. Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Enhancing a model's long-context ability before supervised fine-tuning improves math reasoning accuracy, including on short-input benchmarks.

  4. Domyn-Small: A European 10B Reasoning Language Model

    cs.CL 2026-05 conditional novelty 5.0 of 10

    Domyn-Small is a 10B reasoning LLM that claims to deliver roughly one-third the inference tokens of Qwen3.5-9B at competitive accuracy, though results are marked as preliminary.

  5. StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A training-free, query-agnostic KV cache compression method for streaming video MLLMs, using chat-template attention as a saliency proxy, matches or beats prior streaming methods at a fixed 6K memory budget.

  6. 100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?

    cs.CL 2025-05 conditional novelty 5.0 of 10

    100-LongBench and LongScore evaluate LLMs at controlled context lengths and rank models by relative performance drop from a short-context baseline, not by raw accuracy.

  7. SELF: Self-Extend the Context Length With Logistic Growth Function

    cs.CL 2025-05 conditional novelty 5.0 of 10

    SELF replaces Self-Extend's fixed token grouping with a logistic-growth grouping schedule, giving mixed but sometimes large gains on long-context benchmarks.

  8. LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions

    cs.CL 2025-05 conditional novelty 5.0 of 10

    By prompting an aligned LLM with a document and the special token that precedes a user query, LongMagpie synthesizes long-context instruction data that outperforms prior datasets when used to fine-tune Llama-3-8B.

  9. SciGPT: A Large Language Model for Scientific Literature Understanding and Knowledge Discovery

    cs.CL 2025-09 reject novelty 4.0 of 10

    SciGPT, a fine-tuned Qwen3 model for scientific literature, is reported to outperform GPT-4 on a new ScienceBench benchmark, but the evaluation is unreliable due to missing artifacts and contradictory numbers.

  10. HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models

    cs.CL 2025-09 reject novelty 4.0 of 10

    HoPE replaces RoPE's sine/cosine rotations with hyperbolic functions plus an exponential damping term to enforce monotonic attention decay, but the claimed consistent superiority and the 'RoPE as special case' theorem...

  11. AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

    cs.AI 2025-08 unverdicted novelty 4.0 of 10

    AgentScope 1.0 packages the components needed to build, evaluate, and deploy LLM agent applications into one developer framework.

  12. An Overview of Algorithms for Contactless Cardiac Feature Extraction from Radar Signals: Advances and Challenges

    eess.SP 2025-08 unverdicted novelty 4.0 of 10

    The paper claims to be the first review of signal-processing algorithms for radar-based cardiac monitoring, with a new taxonomy and public dataset listings.

  13. GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A from-scratch Russian MoE LLM family is released with competitive benchmark scores, but key efficiency and novelty claims are not fully evidenced.

Pith tools