Cover Image

The Geometries of Truth Are Orthogonal Across Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Azizian, Waiss, Kirchhof, Michael, Ndiaye, Eugene, Bethune, Louis, Klein, Michal, Ablin, Pierre, Cuturi, Marco
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
by: Kirchhof, Michael, et al.
Published: (2024)

The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining
by: Saada, Thiziri Nait, et al.
Published: (2025)

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
by: Mlodozeniec, Bruno, et al.
Published: (2025)

Multivariate Conformal Prediction using Optimal Transport
by: Klein, Michal, et al.
Published: (2025)

Nectar: Neural Estimation of Cached-Token Attention via Regression
by: Monteiro, João, et al.
Published: (2026)

Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
by: Bethune, Louis, et al.
Published: (2025)

Careful with that Scalpel: Improving Gradient Surgery with an EMA
by: Hsieh, Yu-Guan, et al.
Published: (2024)

Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
by: Kirchhof, Michael, et al.
Published: (2025)

Learning Elastic Costs to Shape Monge Displacements
by: Klein, Michal, et al.
Published: (2023)

Pretraining with hierarchical memories: separating long-tail and common knowledge
by: Pouransari, Hadi, et al.
Published: (2025)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
by: Kwek, Eugene, et al.
Published: (2025)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
by: Yang, Ziyu, et al.
Published: (2026)

DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures
by: Gualdoni, Eleonora, et al.
Published: (2026)

Learning Unmasking Policies for Diffusion Language Models
by: Jazbec, Metod, et al.
Published: (2025)

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis
by: Bennion, Jonathan, et al.
Published: (2025)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
by: Ramesh, Shyam Sundhar, et al.
Published: (2026)

Optimal Splitting of Language Models from Mixtures to Specialized Domains
by: Seto, Skyler, et al.
Published: (2026)

Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
by: Nakkiran, Preetum, et al.
Published: (2025)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
by: Wei, Zhepei, et al.
Published: (2025)

TruthFlow: Truthful LLM Generation via Representation Flow Correction
by: Wang, Hanyu, et al.
Published: (2025)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
by: Zhang, Shaolei, et al.
Published: (2024)

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results
by: Santilli, Andrea, et al.
Published: (2025)

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
by: Kirchhof, Michael, et al.
Published: (2025)

How Does the Pretraining Distribution Shape In-Context Learning? Task Selection, Generalization, and Robustness
by: Azizian, Waïss, et al.
Published: (2025)

Uncertainties of Latent Representations in Computer Vision
by: Kirchhof, Michael
Published: (2024)

Soft Tokens, Hard Truths
by: Butt, Natasha, et al.
Published: (2025)

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
by: Choudhury, Deepro, et al.
Published: (2025)

Robustness as an Emergent Property of Task Performance
by: Ashury-Tahan, Shir, et al.
Published: (2026)

What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers
by: Jacopin, Éric
Published: (2026)

Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks
by: Vatsal, Shubham, et al.
Published: (2025)

Scaling Categorical Flow Maps
by: Davis, Oscar, et al.
Published: (2026)

Ranking Large Language Models without Ground Truth
by: Dhurandhar, Amit, et al.
Published: (2024)

Personas as a Way to Model Truthfulness in Language Models
by: Joshi, Nitish, et al.
Published: (2023)

Orthogonal Finetuning for Direct Preference Optimization
by: Yang, Chenxu, et al.
Published: (2024)

From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
by: Schiekiera, Louis, et al.
Published: (2026)

Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures
by: Vesseron, Nina, et al.
Published: (2025)

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models
by: Liang, Kaiqu, et al.
Published: (2025)

Overthinking the Truth: Understanding how Language Models Process False Demonstrations
by: Halawi, Danny, et al.
Published: (2023)

WolBanking77: Wolof Banking Speech Intent Classification Dataset
by: Kandji, Abdou Karim, et al.
Published: (2025)

Reparameterized LLM Training via Orthogonal Equivalence Transformation
by: Qiu, Zeju, et al.
Published: (2025)