Copertina

Lost in Space: Finding the Right Tokens for Structured Output

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hamilton, Sil, Mimno, David
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
di: Hamilton, Sil, et al.
Pubblicazione: (2026)

The Zero Body Problem: Probing LLM Use of Sensory Language
di: Hicke, Rebecca M. M., et al.
Pubblicazione: (2025)

Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels
di: Hamilton, Sil, et al.
Pubblicazione: (2025)

A City of Millions: Mapping Literary Social Networks At Scale
di: Hamilton, Sil, et al.
Pubblicazione: (2025)

Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries
di: Hicke, Rebecca M. M., et al.
Pubblicazione: (2026)

Detecting Mode Collapse in Language Models via Narration
di: Hamilton, Sil
Pubblicazione: (2024)

The COVID That Wasn't: Counterfactual Journalism Using GPT
di: Hamilton, Sil, et al.
Pubblicazione: (2022)

Stronger Random Baselines for In-Context Learning
di: Yauney, Gregory, et al.
Pubblicazione: (2024)

Weight Tying Biases Token Embeddings Towards the Output Space
di: Lopardo, Antonio, et al.
Pubblicazione: (2026)

[Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs
di: Hicke, Rebecca M. M., et al.
Pubblicazione: (2024)

NarraBench: A Comprehensive Framework for Narrative Benchmarking
di: Hamilton, Sil, et al.
Pubblicazione: (2025)

Looking for the Inner Music: Probing LLMs' Understanding of Literary Style
di: Hicke, Rebecca M. M., et al.
Pubblicazione: (2025)

Show or Tell? Modeling the evolution of request-making in Human-LLM conversations
di: Zhu, Shengqi, et al.
Pubblicazione: (2025)

Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild
di: Zhu, Shengqi, et al.
Pubblicazione: (2026)

Tasks and Roles in Legal AI: Data Curation, Annotation, and Verification
di: Koenecke, Allison, et al.
Pubblicazione: (2025)

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
di: Sun, Jie, et al.
Pubblicazione: (2026)

Topic Modelling: Going Beyond Token Outputs
di: Williams, Lowri, et al.
Pubblicazione: (2024)

Do Chinese models speak Chinese languages?
di: Wen-Yi, Andrea W, et al.
Pubblicazione: (2025)

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
di: Liu, Jiacheng, et al.
Pubblicazione: (2025)

Lost in State Space: Probing Frozen Mamba Representations
di: Wagh, Bhagyashree, et al.
Pubblicazione: (2026)

Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
di: Eisenstein, Jacob, et al.
Pubblicazione: (2022)

The Afterlives of Shakespeare and Company in Online Social Readership
di: Antoniak, Maria, et al.
Pubblicazione: (2024)

Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space
di: Materzok, Tobias
Pubblicazione: (2026)

Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs
di: Hicke, Rebecca M. M., et al.
Pubblicazione: (2025)

Understanding Token Probability Encoding in Output Embeddings
di: Cho, Hakaze, et al.
Pubblicazione: (2024)

How Chinese are Chinese Language Models? The Puzzling Lack of Language Policy in China's LLMs
di: Wen-Yi, Andrea W, et al.
Pubblicazione: (2024)

Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios
di: Toney-Wails, Autumn, et al.
Pubblicazione: (2025)

Dynamic Template Selection for Output Token Generation Optimization: MLP-Based and Transformer Approaches
di: Yadavalli, Bharadwaj
Pubblicazione: (2025)

Lost at the Beginning of Reasoning
di: Liao, Baohao, et al.
Pubblicazione: (2025)

Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs
di: Venkatesh, Sohan
Pubblicazione: (2026)

DRS: Deep Question Reformulation With Structured Output
di: Li, Zhecheng, et al.
Pubblicazione: (2024)

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
di: Cappelletti, Silvia, et al.
Pubblicazione: (2025)

Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
di: Zhang, Tianchen, et al.
Pubblicazione: (2024)

Finding Structure in Language Models
di: Jumelet, Jaap
Pubblicazione: (2024)

Automate or Assist? The Role of Computational Models in Identifying Gendered Discourse in US Capital Trial Transcripts
di: Wen-Yi, Andrea W, et al.
Pubblicazione: (2024)

The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models
di: Singh, Abhinav Kumar, et al.
Pubblicazione: (2026)

Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
di: Deng, Ken, et al.
Pubblicazione: (2026)

Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain
di: Li, Yue, et al.
Pubblicazione: (2025)

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
di: Shen, Zhenyi, et al.
Pubblicazione: (2025)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
di: Wen, Zichen, et al.
Pubblicazione: (2025)