![[2606.01800] Multilinguality of Large Language Models From a Structural Perspective](/static/img/curated/desks/afbytes-tech.png)
[2606.01800] Multilinguality of Large Language Models From a Structural Perspective
Abstract page for arXiv paper 2606.01800: Multilinguality of Large Language Models From a Structural Perspective
America Forever Bytes
Large Language Models · AFBytes
Technology
Large Language Models
Recent coverage
[2606.01845] Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
Abstract page for arXiv paper 2606.01845: Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
[2606.01462] An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
Abstract page for arXiv paper 2606.01462: An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
[2606.01610] Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
Abstract page for arXiv paper 2606.01610: Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
[2605.30524] Representation Collapse in Sequential Post-Training of Large Language Models
Abstract page for arXiv paper 2605.30524: Representation Collapse in Sequential Post-Training of Large Language Models
[2605.30526] Measuring, Localizing, and Ablating Alignment Signatures in LLMs
Abstract page for arXiv paper 2605.30526: Measuring, Localizing, and Ablating Alignment Signatures in LLMs
[2605.30534] Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks
Abstract page for arXiv paper 2605.30534: Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks
[2605.30537] The Long-Term Effects of Data Selection in LLM Fine-Tuning
Abstract page for arXiv paper 2605.30537: The Long-Term Effects of Data Selection in LLM Fine-Tuning
[2605.30539] A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance
Abstract page for arXiv paper 2605.30539: A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance
![[2605.31056] How Much Do LLMs Know About Chinese Zero Pronouns?](/static/img/curated/desks/afbytes-china.png)
[2605.31056] How Much Do LLMs Know About Chinese Zero Pronouns?
Abstract page for arXiv paper 2605.31056: How Much Do LLMs Know About Chinese Zero Pronouns?
[2404.14928] Graph Machine Learning in the Era of Large Language Models (LLMs)
Abstract page for arXiv paper 2404.14928: Graph Machine Learning in the Era of Large Language Models (LLMs)
[2501.04661] Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
Abstract page for arXiv paper 2501.04661: Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
[2605.30675] Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
Abstract page for arXiv paper 2605.30675: Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
[2605.30719] When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
Abstract page for arXiv paper 2605.30719: When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
[2605.31393] Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
Abstract page for arXiv paper 2605.31393: Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
[2605.31404] The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
Abstract page for arXiv paper 2605.31404: The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spati...
[2605.31408] Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study
Abstract page for arXiv paper 2605.31408: Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study
[2605.31445] Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
Abstract page for arXiv paper 2605.31445: Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
[2605.31446] Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction
Abstract page for arXiv paper 2605.31446: Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction
Why Prompt Caching is the Secret to Slashing Your AI Costs By 90%
Learn how prompt caching and KV vectors can reduce your AI API costs by up to 90 percent while improving LLM response latency.
[2605.28854] Large language models reorganize representational geometry during in-context learning
Abstract page for arXiv paper 2605.28854: Large language models reorganize representational geometry during in-context learning
[2605.29548] Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
Abstract page for arXiv paper 2605.29548: Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
[2605.29555] From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals
Abstract page for arXiv paper 2605.29555: From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference ...
[2510.00777] In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
Abstract page for arXiv paper 2510.00777: In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
[2510.06182] Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
Abstract page for arXiv paper 2510.06182: Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
[2605.28826] From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale
Abstract page for arXiv paper 2605.28826: From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale
[2605.29192] ReasonOps: Operator Segmentation for LLM Reasoning Traces
Abstract page for arXiv paper 2605.29192: ReasonOps: Operator Segmentation for LLM Reasoning Traces
[2605.30144] AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
Abstract page for arXiv paper 2605.30144: AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
[2605.30150] Anchorless Diversification for Parallel LLM Ideation
Abstract page for arXiv paper 2605.30150: Anchorless Diversification for Parallel LLM Ideation
[2605.30151] Temporal Stability and Few-Shot Prompting in Math Task Assessment
Abstract page for arXiv paper 2605.30151: Temporal Stability and Few-Shot Prompting in Math Task Assessment