Cover Image

Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Zhaoxin, Ma, Jianfei, Chersoni, Emmanuele, Zhao, Xiaojing, Bao, Xiaoyi
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

From BERT to LLMs: Comparing and Understanding Chinese Classifier Prediction in Language Models
by: Zhang, Ziqi, et al.
Published: (2025)

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy
by: Feng, Zhaoxin, et al.
Published: (2026)

Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures
by: Prange, Jakob, et al.
Published: (2023)

Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
by: Wang, Yu, et al.
Published: (2026)

Is Length Really A Liability? An Evaluation of Multi-turn LLM Conversations using BoolQ
by: Neergaard, Karl, et al.
Published: (2026)

Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs
by: Yang, Yiheng, et al.
Published: (2025)

Composing or Not Composing? Towards Distributional Construction Grammars
by: Blache, Philippe, et al.
Published: (2024)

Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models
by: Kauf, Carina, et al.
Published: (2024)

StockGenChaR: A Study on the Evaluation of Large Vision-Language Models on Stock Chart Captioning
by: Qiu, Le, et al.
Published: (2024)

From the New World of Word Embeddings: A Comparative Study of Small-World Lexico-Semantic Networks in LLMs
by: Liu, Zhu, et al.
Published: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
by: Li, Li, et al.
Published: (2025)

Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
by: Kopiczko, Dawid J., et al.
Published: (2024)

An Evaluation of Sindhi Word Embedding in Semantic Analogies and Downstream Tasks
by: Ali, Wazir, et al.
Published: (2024)

Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings
by: Schuster, Carolin M., et al.
Published: (2024)

Semantic Compression for Word and Sentence Embeddings using Discrete Wavelet Transform
by: Salama, Rana Aref, et al.
Published: (2025)

A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change
by: Periti, Francesco, et al.
Published: (2024)

Static Word Embeddings for Sentence Semantic Representation
by: Wada, Takashi, et al.
Published: (2025)

Looking for the Inner Music: Probing LLMs' Understanding of Literary Style
by: Hicke, Rebecca M. M., et al.
Published: (2025)

TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding
by: Qiang, Minjie, et al.
Published: (2026)

Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness
by: Fan, Xiaojing, et al.
Published: (2024)

Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes
by: Aida, Taichi, et al.
Published: (2024)

Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing
by: Tanwar, Eshaan, et al.
Published: (2025)

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
by: Xu, Kan, et al.
Published: (2021)

Learning Complex Word Embeddings in Classical and Quantum Spaces
by: Harvey, Carys, et al.
Published: (2024)

ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models
by: Miliani, Martina, et al.
Published: (2025)

semantic-features: A User-Friendly Tool for Studying Contextual Word Embeddings in Interpretable Semantic Spaces
by: Ranganathan, Jwalanthi, et al.
Published: (2025)

Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia
by: Wang, Chenxi, et al.
Published: (2025)

Mitigating Gender Bias in Contextual Word Embeddings
by: Yarrabelly, Navya, et al.
Published: (2024)

Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
by: Bao, Yuntai, et al.
Published: (2025)

An Exploratory Analysis on the Explanatory Potential of Embedding-Based Measures of Semantic Transparency for Malay Word Recognition
by: Mohamed, M. Maziyah, et al.
Published: (2025)

One Word Is Not Enough: Simple Prompts Improve Word Embeddings
by: Ranjan, Rajeev
Published: (2025)

Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
by: Chen, Xin, et al.
Published: (2021)

Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker
by: De Lange, Matthias, et al.
Published: (2025)

Correspondence Analysis and PMI-Based Word Embeddings: A Comparative Study
by: Qi, Qianqian, et al.
Published: (2024)

QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions
by: Lei, Jiayin, et al.
Published: (2026)

Revisiting Word Embeddings in the LLM Era
by: Mahajan, Yash, et al.
Published: (2025)

Evaluating Metrics for Bias in Word Embeddings
by: Schröder, Sarah, et al.
Published: (2021)

The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations
by: Soler, Aina Garí, et al.
Published: (2024)

BabyLM's First Words: Word Segmentation as a Phonological Probing Task
by: Goriely, Zébulon, et al.
Published: (2025)

Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings
by: Fabregat-Hernández, Ares, et al.
Published: (2025)