No article text was recorded for this version.
length extrapolation failure
Version 2 of 2368 papers421 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Compositional Generalization for Natural Language Interfaces to Web APIs
- Blog: Understanding Robust Generalization in Learning Regular Languages
- Blog: (How) Do Language Models Track State?
- Blog: Exploring Length Generalization in Large Language Models
- Blog: How Well Can a Long Sequence Model Model Long Sequences? Comparing Architechtural Inductive Biases on Long-Context Abilities
- Blog: Compositionality Decomposed: How do Neural Networks Generalise? (Extended Abstract)
- Blog: Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks
- Blog: The CLRS-Text Algorithmic Reasoning Language Benchmark
- Blog: Are Sample-Efficient NLP Models More Robust?
- Blog: Relating the Seemingly Unrelated: Principled Understanding of Generalization for Generative Models in Arithmetic Reasoning Tasks
- Blog: Understanding Robust Generalization in Learning Regular Languages
- Blog: WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval
- Blog: Provable Length Generalization in Sequence Prediction via Spectral Filtering
- Blog: The Missing Alignment Link of In-context Learning on Sequences
- Blog: DeciMamba: Exploring the Length Extrapolation Potential of Mamba
- Blog: Exploring the Relationship Between Model Architecture and In-Context Learning Ability
- Blog: Location Attention for Extrapolation to Longer Sequences
- Blog: Learning and Generalization in RNNs
- Blog: SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation
- Blog: A Controlled Study on Long Context Extension and Generalization in LLMs
- Blog: Compositional generalization through meta sequence-to-sequence learning
- Blog: The Role of Sparsity for Length Generalization in LLMs
- Blog: TULIP: Token-length Upgraded CLIP
- Blog: On Generalization for Generative Flow Networks
- Blog: SLOG: A Structural Generalization Benchmark for Semantic Parsing
- Blog: Sequence Length is a Domain: Length-based Overfitting in Transformer Models
- Blog: Data Engineering for Scaling Language Models to 128K Context
- Blog: A Controlled Study on Long Context Extension and Generalization in LLMs
- Blog: Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
- Blog: Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
- Blog: Filter Equivariant Functions: A symmetric account of length-general extrapolation on lists
- Blog: Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
- Blog: Transformers Learn Shortcuts to Automata
- Blog: Transformers Learn Shortcuts to Automata
- Blog: Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning
- Blog: Non-Asymptotic Length Generalization
- Blog: On the Generalization Ability of Next-Token-Prediction Pretraining
- Blog: How Well Can a Long Sequence Model Model Long Sequences? Comparing Architectural Inductive Biases on Long-Context Abilities
- Blog: Verification of Recurrent Neural Networks Through Rule Extraction
- Blog: Advancing Regular Language Reasoning in Linear Recurrent Neural Networks
- Blog: Are Sample-Efficient NLP Models More Robust?
- Blog: Blocksworld Revisited: Learning and Reasoning to Generate Event-Sequences from Image Pairs
- Blog: How do autoregressive transformers solve full addition?
- Blog: Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings
- Blog: Summarization with Precise Length Control
- Blog: The Surprising Computational Power of Nondeterministic Stack RNNs
- Blog: SEED-Story: Multimodal Long Story Generation with Large Language Model
- Blog: Generalization Bounds for Weighted Automata
- Blog: Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences
- Blog: On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages
- Blog: AnyEdit: Edit Any Knowledge Encoded in Language Models
- Blog: On the Power of Convolution-Augmented Transformer
- Blog: Out of Length Text Recognition with Sub-String Matching
- Blog: Enhancing Length Generalization for Attention Based Knowledge Tracing Models with Linear Biases
- Blog: Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages
- Blog: GAMformer: In-Context Learning for Generalized Additive Models
- Blog: Scaling ASR Improves Zero and Few Shot Learning
- Blog: HELM: Hierarchical Encoding for mRNA Language Modeling
- Blog: Learning Neural Programs To Parse Programs
- Blog: PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
Showing 60 of 368 papers.
History & citation
Current · Permanent link
- Sample Complexity Barriers in Language Generation merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_length_extrapolation_failure_56499dff,
title = {length extrapolation failure},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/length-extrapolation-failure/rdr_56499dfff37743b08a28e6ffce563f17},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_length_extrapolation_failure_56499dff_v2,
title = {length extrapolation failure},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/length-extrapolation-failure/rdr_56499dfff37743b08a28e6ffce563f17/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}