Cover Image

FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kowsher, Md, Prottasha, Nusrat Jahan, Xu, Shiyun, Mohanto, Shetu, Garibay, Ozlem, Yousefi, Niloofar, Chen, Chen
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Does Self-Attention Need Separate Weights in Transformers?
by: Kowsher, Md, et al.
Published: (2024)

Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning
by: Prottasha, Nusrat Jahan, et al.
Published: (2024)

LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting
by: Kowsher, Md, et al.
Published: (2024)

Predicting Through Generation: Why Generation Is Better for Prediction
by: Kowsher, Md, et al.
Published: (2025)

Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning
by: Prottasha, Nusrat Jahan, et al.
Published: (2026)

User Profile with Large Language Models: Construction, Updating, and Benchmarking
by: Prottasha, Nusrat Jahan, et al.
Published: (2025)

PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models
by: Prottasha, Nusrat Jahan, et al.
Published: (2025)

Propulsion: Steering LLM with Tiny Fine-Tuning
by: Kowsher, Md, et al.
Published: (2024)

LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
by: Kowsher, Md, et al.
Published: (2026)

Explainable Detection of Implicit Influential Patterns in Conversations via Data Augmentation
by: Abdidizaji, Sina, et al.
Published: (2025)

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

BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting
by: Basher, Mohammad Jahid Ibna, et al.
Published: (2025)

Token Trails: Navigating Contextual Depths in Conversational AI with ChatLLM
by: Kowsher, Md., et al.
Published: (2024)

RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates
by: Kowsher, Md, et al.
Published: (2024)

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
by: Hossain, Elias, et al.
Published: (2026)

Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability
by: Lia, Nusrat Jahan, et al.
Published: (2026)

Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer
by: Kowsher, Md, et al.
Published: (2024)

BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance
by: Hossain, Elias, et al.
Published: (2025)

Learning Stable Predictors from Weak Supervision under Distribution Shift
by: Shoeibi, Mehrdad, et al.
Published: (2026)

Prompting Large Language Models to Detect Dementia Family Caregivers
by: Biswas, Md Badsha, et al.
Published: (2025)

Enhancing Bangla Language Next Word Prediction and Sentence Completion through Extended RNN with Bi-LSTM Model On N-gram Language
by: Islam, Md Robiul, et al.
Published: (2024)

Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis
by: Cheng, Zhenxiao, et al.
Published: (2024)

When AI Does Science: Evaluating the Autonomous AI Scientist KOSMOS in Radiation Biology
by: Nusrat, Humza, et al.
Published: (2025)

Protecting Your LLMs with Information Bottleneck
by: Liu, Zichuan, et al.
Published: (2024)

Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code
by: McCully, Gary A., et al.
Published: (2024)

Exploring Cross-Lingual Knowledge Transfer via Transliteration-Based MLM Fine-Tuning for Critically Low-resource Chakma Language
by: Khisa, Adity, et al.
Published: (2025)

SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
by: Kowsher, Md, et al.
Published: (2025)

Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
by: Zhang, Jun, et al.
Published: (2026)

Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM
by: Biswas, Md Badsha, et al.
Published: (2026)

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture
by: Fu, Biao, et al.
Published: (2025)

A Benchmark Study of Segmentation Models and Adaptation Strategies for Landslide Detection from Satellite Imagery
by: Kowsher, Md, et al.
Published: (2026)

Evaluating the Effectiveness of Cost-Efficient Large Language Models in Benchmark Biomedical Tasks
by: Jahan, Israt, et al.
Published: (2025)

Gradient descent with generalized Newton's method
by: Bu, Zhiqi, et al.
Published: (2024)

Text Sentiment Analysis and Classification Based on Bidirectional Gated Recurrent Units (GRUs) Model
by: Xu, Wei, et al.
Published: (2024)

Missing vs. Unused Knowledge Hypothesis for Language Model Bottlenecks in Patent Understanding
by: Wu, Siyang, et al.
Published: (2025)

The Generalization Ridge: Information Flow in Natural Language Generation
by: Chang, Ruidi, et al.
Published: (2025)

Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision
by: Yoshida, Ryo, et al.
Published: (2024)

Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification
by: Chowdhury, Masnun Nuha, et al.
Published: (2026)

Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models
by: Yousefi, Safoora, et al.
Published: (2023)

MedGemma vs GPT-4: Open-Source and Proprietary Zero-shot Medical Disease Classification from Images
by: Prottasha, Md. Sazzadul Islam, et al.
Published: (2025)