Cover Image

Geometric Latent Reasoning Induces Shorter Generations in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumar, Shashi, Kaloga, Yacouba, Motlicek, Petr, Kodrasi, Ina, Cavallaro, Andrea
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

A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport
by: Kaloga, Yacouba, et al.
Published: (2025)

Latent Space Factorization in LoRA
by: Kumar, Shashi, et al.
Published: (2025)

Towards interpretable emotion recognition: Identifying key features with machine learning
by: Kaloga, Yacouba, et al.
Published: (2025)

CLAP-Based Automatic Word Naming Recognition in Post-Stroke Aphasia
by: Kaloga, Yacouba, et al.
Published: (2026)

Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection
by: Kaloga, Yacouba, et al.
Published: (2024)

Graph Neural Networks for Parkinsons Disease Detection
by: Sheikh, Shakeel A., et al.
Published: (2024)

Evaluation of Automatic Speech Recognition Using Generative Large Language Models
by: Bañeras-Roux, Thibault, et al.
Published: (2026)

Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction
by: Burdisso, Sergio, et al.
Published: (2024)

Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews
by: Burdisso, Sergio, et al.
Published: (2023)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
by: Thorbecke, Iuliia, et al.
Published: (2024)

TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR
by: Kumar, Shashi, et al.
Published: (2024)

On Code-Induced Reasoning in LLMs
by: Waheed, Abdul, et al.
Published: (2025)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
by: Hassid, Michael, et al.
Published: (2025)

Listen, Attend, Understand: a Regularization Technique for Stable E2E Speech Translation Training on High Variance labels
by: Diarra, Yacouba, et al.
Published: (2026)

Reliability Estimation of News Media Sources: Birds of a Feather Flock Together
by: Burdisso, Sergio, et al.
Published: (2024)

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation
by: Kumar, Shashi, et al.
Published: (2025)

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR
by: Bañeras-Roux, Thibault, et al.
Published: (2026)

Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection
by: Burdisso, Sergio, et al.
Published: (2026)

Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
by: Kumar, Shashi, et al.
Published: (2024)

Improving Latent Reasoning in LLMs via Soft Concept Mixing
by: Wang, Kang, et al.
Published: (2025)

Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression
by: Zeng, Lingjie, et al.
Published: (2026)

C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness
by: Kang, Yu, et al.
Published: (2024)

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs
by: Wu, Yang, et al.
Published: (2025)

JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation
by: Liu, Bingyang Kelvin, et al.
Published: (2025)

Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR
by: Kumar, Shashi, et al.
Published: (2026)

Unifying Global and Near-Context Biasing in a Single Trie Pass
by: Thorbecke, Iuliia, et al.
Published: (2024)

Text-only adaptation in LLM-based ASR through text denoising
by: Carofilis, Andrés, et al.
Published: (2026)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
by: Shi, Dachuan, et al.
Published: (2025)

Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering
by: Carofilis, Andres, et al.
Published: (2025)

Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering
by: Rangappa, Pradeep, et al.
Published: (2025)

Cost Analysis of Human-corrected Transcription for Predominately Oral Languages
by: Diarra, Yacouba, et al.
Published: (2025)

Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs
by: Orlicki, José I.
Published: (2025)

CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
by: He, Jie, et al.
Published: (2025)

ALARM: Audio-Language Alignment for Reasoning Models
by: Grinberg, Petr, et al.
Published: (2026)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
by: Jiang, Houcheng, et al.
Published: (2026)

Specializing General-purpose LLM Embeddings for Implicit Hate Speech Detection across Datasets
by: Cheremetiev, Vassiliy, et al.
Published: (2025)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
by: Sheshanarayana, Disha, et al.
Published: (2026)

Variational Autoencoder for Personalized Pathological Speech Enhancement
by: Hou, Mingchi, et al.
Published: (2025)

Influence of Clean Speech Characteristics on Speech Enhancement Performance
by: Hou, Mingchi, et al.
Published: (2025)

Suppressing Noise Disparity in Training Data for Automatic Pathological Speech Detection
by: Amiri, Mahdi, et al.
Published: (2024)