Cover Image

Understanding Textual Capability Degradation in Speech LLMs via Parameter Importance Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chao, Zheng, Rui-Chen, Ai, Yang, Ling, Zhen-Hua
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
by: Tan, Nelvin, et al.
Published: (2025)

DeepInnovator: Triggering the Innovative Capabilities of LLMs
by: Fan, Tianyu, et al.
Published: (2026)

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
by: Chen, Jingxiang, et al.
Published: (2026)

CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language
by: Zhao, Rui, et al.
Published: (2026)

Preservation of Language Understanding Capabilities in Speech-aware Large Language Models
by: Kubis, Marek, et al.
Published: (2025)

Speech-based Psychological Crisis Assessment using LLMs
by: Chiba, Terumi, et al.
Published: (2026)

DentalBench: Benchmarking and Advancing LLMs Capability for Bilingual Dentistry Understanding
by: Zhu, Hengchuan, et al.
Published: (2025)

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving
by: Dou, Shihan, et al.
Published: (2025)

SAFT: Structure-aware Transformers for Textual Interaction Classification
by: Wang, Hongtao, et al.
Published: (2025)

Are Your LLMs Capable of Stable Reasoning?
by: Liu, Junnan, et al.
Published: (2024)

Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity
by: Wu, Xinwei, et al.
Published: (2025)

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
by: Feng, Guhao, et al.
Published: (2024)

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
by: Cao, Di, et al.
Published: (2026)

A Closer Look into LLMs for Table Understanding
by: Wang, Jia, et al.
Published: (2026)

Scaling Textual Gradients via Sampling-Based Momentum
by: Ding, Zixin, et al.
Published: (2025)

TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
by: Li, Zhuofeng, et al.
Published: (2024)

Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean
by: Park, Chanwoo, et al.
Published: (2025)

Explore the Reasoning Capability of LLMs in the Chess Testbed
by: Wang, Shu, et al.
Published: (2024)

Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data
by: Wang, Qiongqiong, et al.
Published: (2025)

SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models
by: Yang, Wanqi, et al.
Published: (2025)

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context
by: Ruan, Kai, et al.
Published: (2024)

EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs
by: Xu, Wanghan, et al.
Published: (2025)

Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning
by: Li, Zhen, et al.
Published: (2025)

Beyond Textual Context: Structural Graph Encoding with Adaptive Space Alignment to alleviate the hallucination of LLMs
by: Zhang, Yifang, et al.
Published: (2025)

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
by: Wang, Hanbin, et al.
Published: (2025)

A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English
by: Bäumler, Julian, et al.
Published: (2025)

Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
by: Zhou, Qinhao, et al.
Published: (2024)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
by: Wang, Xu, et al.
Published: (2025)

High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
by: Franzmeyer, Tim, et al.
Published: (2025)

An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs
by: Vyas, Kaustubh, et al.
Published: (2025)

Empowering Dysarthric Speech: Leveraging Advanced LLMs for Accurate Speech Correction and Multimodal Emotion Analysis
by: Attaluri, Kaushal, et al.
Published: (2024)

Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence
by: Ye, Fengying, et al.
Published: (2025)

Node Importance Estimation Leveraging LLMs for Semantic Augmentation in Knowledge Graphs
by: Lin, Xinyu, et al.
Published: (2024)

HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning
by: Jiang, Zhuohang, et al.
Published: (2025)

Assessing the Capabilities of LLMs in Humor:A Multi-dimensional Analysis of Oogiri Generation and Evaluation
by: Sakabe, Ritsu, et al.
Published: (2025)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
by: Yu, Ye, et al.
Published: (2026)

The World According to LLMs: How Geographic Origin Influences LLMs' Entity Deduction Capabilities
by: Lalai, Harsh Nishant, et al.
Published: (2025)

SynDec: A Synthesize-then-Decode Approach for Arbitrary Textual Style Transfer via Large Language Models
by: Sun, Han, et al.
Published: (2025)

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
by: Sun, Huashan, et al.
Published: (2025)

Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
by: Zhang, Zheng, et al.
Published: (2024)