Image de couverture de livre

Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bajaj, Anooshka, Mistry, Deven Mahesh, Maini, Sahaj Singh, Aggarwal, Yash, Tiganj, Zoran
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training
par: Mistry, Deven Mahesh, et autres
Publié: (2025)

Temporal Dependencies in In-Context Learning: The Role of Induction Heads
par: Bajaj, Anooshka, et autres
Publié: (2026)

Who Do LLMs Trust? Human Experts Matter More Than Other LLMs
par: Bajaj, Anooshka, et autres
Publié: (2026)

High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination
par: Maini, Sahaj Singh, et autres
Publié: (2026)

Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows
par: Dickson, Billy, et autres
Publié: (2025)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
par: Kabir, Md Rysul, et autres
Publié: (2026)

Vision-language models learn the geometry of human perceptual space
par: Sanders, Craig, et autres
Publié: (2025)

REAMS: Reasoning Enhanced Algorithm for Maths Solving
par: Singh, Eishkaran, et autres
Publié: (2025)

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO
par: Pappone, Francesco, et autres
Publié: (2025)

Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures
par: Wang, Shenran, et autres
Publié: (2025)

Deep reinforcement learning with time-scale invariant memory
par: Kabir, Md Rysul, et autres
Publié: (2024)

DateLogicQA: Benchmarking Temporal Biases in Large Language Models
par: Bhatia, Gagan, et autres
Publié: (2024)

Neurosymbolic Retrievers for Retrieval-augmented Generation
par: Saxena, Yash, et autres
Publié: (2026)

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
par: Rajesh, Shreyas, et autres
Publié: (2025)

Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
par: Das, Rocktim Jyoti, et autres
Publié: (2023)

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)
par: Wang, Peidong
Publié: (2026)

Unveiling Divergent Inductive Biases of LLMs on Temporal Data
par: Kishore, Sindhu, et autres
Publié: (2024)

State Design Matters: How Representations Shape Dynamic Reasoning in Large Language Models
par: Wong, Annie, et autres
Publié: (2026)

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
par: Fein, Daniel, et autres
Publié: (2026)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
par: Aggarwal, Pranjal, et autres
Publié: (2025)

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
par: Bouchard, Dylan, et autres
Publié: (2026)

From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
par: Li, Lehui, et autres
Publié: (2026)

How Small Transformation Expose the Weakness of Semantic Similarity Measures
par: Nikiema, Serge Lionel, et autres
Publié: (2025)

Mitigating Social Biases in Language Models through Unlearning
par: Dige, Omkar, et autres
Publié: (2024)

RexBERT: Context Specialized Bidirectional Encoders for E-commerce
par: Bajaj, Rahul, et autres
Publié: (2026)

Mining Beyond the Bools: Learning Data Transformations and Temporal Specifications
par: Kouteili, Sam Nicholas, et autres
Publié: (2026)

Neural Retrievers are Biased Towards LLM-Generated Content
par: Dai, Sunhao, et autres
Publié: (2023)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
par: Adarsh, Shivam, et autres
Publié: (2026)

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
par: Bochkov, A.
Publié: (2025)

Transformer-based Joint Modelling for Automatic Essay Scoring and Off-Topic Detection
par: Das, Sourya Dipta, et autres
Publié: (2024)

NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness
par: Singhal, Manav, et autres
Publié: (2024)

TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
par: Wu, Bingheng, et autres
Publié: (2025)

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators
par: Bansal, Hritik, et autres
Publié: (2025)

Do Biased Models Have Biased Thoughts?
par: Rajwal, Swati, et autres
Publié: (2025)

Repeat After Me: Transformers are Better than State Space Models at Copying
par: Jelassi, Samy, et autres
Publié: (2024)

Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models
par: Siddiqui, Saad Mashkoor, et autres
Publié: (2025)

Automated Extraction and Creation of FBS Design Reasoning Knowledge Graphs from Structured Data in Product Catalogues Lacking Contextual Information
par: Sahadevan, Vijayalaxmi, et autres
Publié: (2024)

Semantic Tokens in Retrieval Augmented Generation
par: Suro, Joel
Publié: (2024)

How do Transformer Embeddings Represent Compositions? A Functional Analysis
par: Nagar, Aishik, et autres
Publié: (2025)

Revisiting the Shape Convention of Transformer Language Models
par: Liao, Feng-Ting, et autres
Publié: (2026)