Image de couverture de livre

À la recherche du sens perdu: your favourite LLM might have more to say than you can understand

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Erziev, K. O. T.
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

BSBench: will your LLM find the largest prime number?
par: Erziev, K. O. T.
Publié: (2025)

Revealing economic facts: LLMs know more than they say
par: Buckmann, Marcus, et autres
Publié: (2025)

Is poisoning a real threat to LLM alignment? Maybe more so than you think
par: Pathmanathan, Pankayaraj, et autres
Publié: (2024)

Let your LLM generate a few tokens and you will reduce the need for retrieval
par: Déjean, Hervé
Publié: (2024)

My LLM might Mimic AAE -- But When Should it?
par: Sandoval, Sandra C., et autres
Publié: (2025)

Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4
par: Gema, Aryo Pradipta, et autres
Publié: (2024)

The boosted HP filter is more general than you might think
par: Mei, Ziwei, et autres
Publié: (2022)

The 2020 US Decennial Census is more private than you (might) think
par: Su, Buxin, et autres
Publié: (2024)

The MLIR Transform Dialect. Your compiler is more powerful than you think
par: Lücke, Martin Paul, et autres
Publié: (2024)

Le sens de la famille : analyse du vocabulaire de la parent{é} par les plongements de mots
par: Tanguy, Ludovic, et autres
Publié: (2024)

Pushing for change: have your say
par: Elizabeth Mullineaux
Publié: (2025)

What you say or how you say it? Predicting Conflict Outcomes in Real and LLM-Generated Conversations
par: D'Costa, Priya Ronald, et autres
Publié: (2024)

Chain-of-Description: What I can understand, I can put into words
par: Guo, Jiaxin, et autres
Publié: (2025)

GPT-4 is judged more human than humans in displaced and inverted Turing tests
par: Rathi, Ishika, et autres
Publié: (2024)

Don't lie to your friends: Learning what you know from collaborative self-play
par: Eisenstein, Jacob, et autres
Publié: (2025)

Stop saying LLM: Large Discourse Models (LDM) and Artificial Discursive Agent (ADA)?
par: Lakel, Amar
Publié: (2025)

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
par: Snell, Charlie, et autres
Publié: (2024)

MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit
par: Zhang, Boning, et autres
Publié: (2024)

What your brain activity says about you: A review of neuropsychiatric disorders identified in resting-state and sleep EEG data
par: Scanlon, J. E. M., et autres
Publié: (2025)

I run as fast as a rabbit, can you? A Multilingual Simile Dialogue Dataset
par: Ma, Longxuan, et autres
Publié: (2023)

Language models can learn implicit multi-hop reasoning, but only if they have lots of training data
par: Yao, Yuekun, et autres
Publié: (2025)

LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services
par: Łazuka, Małgorzata, et autres
Publié: (2024)

Who are you, ChatGPT? Personality and Demographic Style in LLM-Generated Content
par: Porat, Dana Sotto, et autres
Publié: (2025)

Did somebody say "Gest-IT"? A pilot exploration of multimodal data management
par: Pannitto, Ludovica, et autres
Publié: (2024)

"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
par: Koudounas, Alkis, et autres
Publié: (2025)

DocLLM: A layout-aware generative language model for multimodal document understanding
par: Wang, Dongsheng, et autres
Publié: (2023)

Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss
par: Xu, Jing, et autres
Publié: (2023)

I can tell whether you are a Native Hawlêri Speaker! How ANN, CNN, and RNN perform in NLI-Native Language Identification
par: Garari, Hardi, et autres
Publié: (2026)

Are LLM-generated plain language summaries truly understandable? A large-scale crowdsourced evaluation
par: Guo, Yue, et autres
Publié: (2025)

‛Until you're in the chair and executing your role, you don't know’: A qualitative study of the needs and perspectives of people with stroke‐related communication disabilities when returning to vocational activity
par: Lucette Lanyon, et autres
Publié: (2024)

Next Token Perception Score: Analytical Assessment of your LLM Perception Skills
par: Cheng, Yu-Ang, et autres
Publié: (2025)

À la recherche du temps perdu: will AI and 150 years of human movement research drive the next Neuroscience revolution?
par: Alessandro D'Ausilio
Publié: (2025)

If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems
par: Chang, Jiamin, et autres
Publié: (2026)

Language models and brains align due to more than next-word prediction and word-level information
par: Merlin, Gabriele, et autres
Publié: (2022)

ReZero: Enhancing LLM search ability by trying one-more-time
par: Dao, Alan, et autres
Publié: (2025)

Introduction - Language Planning: Where have we been? Where might we be going?
par: Richard B. Baldauf Jr.
Publié: (2012)

Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation
par: Kwartler, Ted, et autres
Publié: (2024)

LCA and energy efficiency in buildings: mapping more than twenty years of research
par: Asdrubali, F., et autres
Publié: (2024)

The United States. Oh, say, can you see?
Publié: (2000)

Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages
par: Su, Zeli, et autres
Publié: (2025)