Cover Image

Disentangling Geometry, Performance, and Training in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kulkarni, Atharva, Springer, Jacob Mitchell, Subramonian, Arjun, Swayamdipta, Swabha
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Annotating FrameNet via Structure-Conditioned Language Generation
by: Cui, Xinyue, et al.
Published: (2024)

How Reliable is Language Model Micro-Benchmarking?
by: Yauney, Gregory, et al.
Published: (2025)

Compare without Despair: Reliable Preference Evaluation with Generation Separability
by: Ghosh, Sayan, et al.
Published: (2024)

Improving Language Model Personas via Rationalization with Psychological Scaffolds
by: Joshi, Brihi, et al.
Published: (2025)

Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
by: Ethayarajh, Kawin, et al.
Published: (2021)

Better Language Model Inversion by Compactly Representing Next-Token Distributions
by: Nazir, Murtaza, et al.
Published: (2025)

Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP
by: Gautam, Vagrant, et al.
Published: (2024)

Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?
by: Khurana, Urja, et al.
Published: (2024)

Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification
by: Liu, Joseph, et al.
Published: (2025)

Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
by: Cui, Xinyue, et al.
Published: (2025)

Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations
by: He, Keyu, et al.
Published: (2025)

Teaching Models to Understand (but not Generate) High-risk Data
by: Wang, Ryan, et al.
Published: (2025)

Logits of API-Protected LLMs Leak Proprietary Information
by: Finlayson, Matthew, et al.
Published: (2024)

Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
by: Kulkarni, Atharva, et al.
Published: (2025)

BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity
by: Diddee, Harshita, et al.
Published: (2026)

Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs
by: Ghosh, Sayan, et al.
Published: (2025)

ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations
by: Joshi, Brihi, et al.
Published: (2025)

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge
by: Howard, Phillip, et al.
Published: (2023)

Understanding Catastrophic Forgetting in Language Models via Implicit Inference
by: Kotha, Suhas, et al.
Published: (2023)

Understanding "Democratization" in NLP and ML Research
by: Subramonian, Arjun, et al.
Published: (2024)

Side-by-side Comparison Amplifies Dialect Bias in Language Models
by: Kondapally, Kritee, et al.
Published: (2026)

Generative Explanations for Program Synthesizers
by: Nazari, Amirmohammad, et al.
Published: (2024)

Repetition Improves Language Model Embeddings
by: Springer, Jacob Mitchell, et al.
Published: (2024)

Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis
by: Hengle, Amey, et al.
Published: (2024)

IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language
by: Chance, Christina, et al.
Published: (2026)

OATH-Frames: Characterizing Online Attitudes Towards Homelessness with LLM Assistants
by: Ranjit, Jaspreet, et al.
Published: (2024)

Every Language Model Has a Forgery-Resistant Signature
by: Finlayson, Matthew, et al.
Published: (2025)

ChEmREF: Evaluating Language Model Readiness for Chemical Emergency Response
by: Surana, Risha, et al.
Published: (2025)

Agree to Disagree? A Meta-Evaluation of LLM Misgendering
by: Subramonian, Arjun, et al.
Published: (2025)

Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems
by: Kulkarni, Ajinkya, et al.
Published: (2025)

Why Fine-Tuning Encourages Hallucinations and How to Fix It
by: Kaplan, Guy, et al.
Published: (2026)

Are We Automating the Joy Out of Work? Designing AI to Augment Work, Not Meaning
by: Ranjit, Jaspreet, et al.
Published: (2026)

Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models
by: Mehta, Atharva, et al.
Published: (2025)

Overtrained Language Models Are Harder to Fine-Tune
by: Springer, Jacob Mitchell, et al.
Published: (2025)

Understanding the Influence of Synthetic Data for Text Embedders
by: Springer, Jacob Mitchell, et al.
Published: (2025)

Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR
by: Kulkarni, Ajinkya, et al.
Published: (2026)

Annotations Mitigate Post-Training Mode Collapse
by: Springer, Jacob Mitchell, et al.
Published: (2026)

Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
by: Jones, Erik, et al.
Published: (2025)

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
by: Watts, Ishaan, et al.
Published: (2026)

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
by: Yu, Le, et al.
Published: (2024)