Cover Image

Sparse Semantic Dimension as a Generalization Certificate for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bandyopadhyay, Dibyanayan, Ekbal, Asif
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes
by: Bandyopadhyay, Dibyanayan, et al.
Published: (2024)

Thinking Machines: A Survey of LLM based Reasoning Strategies
by: Bandyopadhyay, Dibyanayan, et al.
Published: (2025)

CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation
by: Bandyopadhyay, Dibyanayan, et al.
Published: (2025)

Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
by: Gain, Baban, et al.
Published: (2025)

Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages
by: Gain, Baban, et al.
Published: (2023)

M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought
by: Kumari, Gitanjali, et al.
Published: (2024)

Can Large Language Models Unlock Novel Scientific Research Ideas?
by: Kumar, Sandeep, et al.
Published: (2024)

'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviews
by: Kumar, Sandeep, et al.
Published: (2024)

The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
by: Nawrot, Piotr, et al.
Published: (2025)

A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information
by: Kapil, Prashant, et al.
Published: (2024)

Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs
by: Kumar, Deepak, et al.
Published: (2026)

Overview of Factify5WQA: Fact Verification through 5W Question-Answering
by: Suresh, Suryavardan, et al.
Published: (2024)

Shh, don't say that! Domain Certification in LLMs
by: Emde, Cornelius, et al.
Published: (2025)

Deep Learning-based Sentiment Analysis of Olympics Tweets
by: Bandyopadhyay, Indranil, et al.
Published: (2024)

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
by: Zheng, Carolina, et al.
Published: (2025)

Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning Strategies
by: Kumar, Nitesh, et al.
Published: (2024)

ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos
by: Phukan, Arpan, et al.
Published: (2024)

ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
by: Liu, Hongyi, et al.
Published: (2025)

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

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
by: Muchane, Mark, et al.
Published: (2025)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
by: Christopoulou, Fenia, et al.
Published: (2024)

CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation
by: Wang, Qinsi, et al.
Published: (2024)

LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models
by: Abdelhalim, Alhassan, et al.
Published: (2026)

DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
by: Ganon, Ben, et al.
Published: (2024)

Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data
by: Gill, Waris, et al.
Published: (2025)

Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates
by: Lamaakal, Ismail, et al.
Published: (2026)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
by: Deiseroth, Björn, et al.
Published: (2024)

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
by: Liu, Jinzhe, et al.
Published: (2025)

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs
by: Harshavardhan
Published: (2026)

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
by: Jiang, Huiqiang, et al.
Published: (2024)

Semantic Refinement with LLMs for Graph Representations
by: Thapaliya, Safal, et al.
Published: (2025)

Teaching LLMs How to Learn with Contextual Fine-Tuning
by: Choi, Younwoo, et al.
Published: (2025)

A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation
by: Gu, Jian, et al.
Published: (2025)

Mitigating Semantic Drift: Evaluating LLMs' Efficacy in Psychotherapy through MI Dialogue Summarization
by: Kumar, Vivek, et al.
Published: (2025)

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
by: Guo, Song, et al.
Published: (2024)

L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMs
by: Kowsher, Md., et al.
Published: (2023)

PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimization
by: Jaisankar, Vijay, et al.
Published: (2024)

Towards Automated Kernel Generation in the Era of LLMs
by: Yu, Yang, et al.
Published: (2026)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
by: Jørgensen, Mikkel Godsk, et al.
Published: (2026)

Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
by: Peng, Dan, et al.
Published: (2025)