Image de couverture de livre

The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Baeumel, Tanja, van Genabith, Josef, Ostermann, Simon
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms
par: Baeumel, Tanja, et autres
Publié: (2026)

Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models
par: Gurgurov, Daniil, et autres
Publié: (2025)

Modular Arithmetic: Language Models Solve Math Digit by Digit
par: Baeumel, Tanja, et autres
Publié: (2025)

Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
par: Gurgurov, Daniil, et autres
Publié: (2025)

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
par: Ghussin, Yusser Al, et autres
Publié: (2026)

Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers
par: Vijayakumar, Soniya, et autres
Publié: (2024)

CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
par: Gurgurov, Daniil, et autres
Publié: (2026)

On Multilingual Encoder Language Model Compression for Low-Resource Languages
par: Gurgurov, Daniil, et autres
Publié: (2025)

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages
par: Gurgurov, Daniil, et autres
Publié: (2025)

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
par: Shi, Dan, et autres
Publié: (2026)

The Latin Substrate: How Language Models Represent and Mediate Script Choice
par: Gurgurov, Daniil, et autres
Publié: (2026)

Multilingual Political Views of Large Language Models: Identification and Steering
par: Gurgurov, Daniil, et autres
Publié: (2025)

ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance
par: Gurgurov, Daniil, et autres
Publié: (2026)

DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
par: Ghussin, Yusser Al, et autres
Publié: (2026)

AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models
par: Hossain, Sayed Muddashir, et autres
Publié: (2025)

From Weights to Activations: Is Steering the Next Frontier of Adaptation?
par: Ostermann, Simon, et autres
Publié: (2026)

Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution
par: Anikina, Tatiana, et autres
Publié: (2025)

Sign Language Translation with Sentence Embedding Supervision
par: Hamidullah, Yasser, et autres
Publié: (2025)

What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations
par: Trinley, Katharina, et autres
Publié: (2025)

Spatio-temporal Sign Language Representation and Translation
par: Hamidullah, Yasser, et autres
Publié: (2025)

When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification
par: Shcharbakova, Hanna, et autres
Publié: (2025)

Seeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Media
par: Yazdani, Shakib, et autres
Publié: (2025)

When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation
par: Tan, David, et autres
Publié: (2026)

Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese
par: Borah, Angana, et autres
Publié: (2023)

Rewiring the Transformer with Depth-Wise LSTMs
par: Xu, Hongfei, et autres
Publié: (2020)

The AI Language Proficiency Monitor -- Tracking the Progress of LLMs on Multilingual Benchmarks
par: Pomerenke, David, et autres
Publié: (2025)

A Critical Study of Automatic Evaluation in Sign Language Translation
par: Yazdani, Shakib, et autres
Publié: (2025)

SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
par: Hamidullah, Yasser, et autres
Publié: (2025)

When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages
par: Bafna, Niyati, et autres
Publié: (2023)

PETra: A Multilingual Corpus of Pragmatic Explicitation in Translation
par: Osmelak, Doreen, et autres
Publié: (2025)

Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters
par: Gurgurov, Daniil, et autres
Publié: (2024)

Automatic Fact-checking in English and Telugu
par: Chikkala, Ravi Kiran, et autres
Publié: (2025)

DualFact+: A Multimodal Fact Verification Framework for Procedural Video Understanding
par: Oguz, Cennet, et autres
Publié: (2026)

Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
par: Zhang, Yitong, et autres
Publié: (2026)

Judge Circuits
par: Feldhus, Nils, et autres
Publié: (2026)

Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
par: Belanec, Robert, et autres
Publié: (2024)

Lookahead Routing for Large Language Models
par: Huang, Canbin, et autres
Publié: (2025)

LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations
par: Wang, Qianli, et autres
Publié: (2024)

Causal Attention with Lookahead Keys
par: Song, Zhuoqing, et autres
Publié: (2025)

Constrained Decoding with Speculative Lookaheads
par: Nakshatri, Nishanth, et autres
Publié: (2024)