No article text was recorded for this version.
limited model scope (cross-architecture validation)
Version 1 of 1452 papers453 conceptsfrozen 2026-10-04
Papers in this version
- Blog: JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning
- Blog: Steering Conversational Large Language Models for Long Emotional Support Conversations
- Blog: Imperfect Visual Verification for Code Edition : A Case Study on TikZ
- Blog: ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language Models
- Blog: Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models
- Blog: An Empirical Study on Prompt Compression for Large Language Models
- Blog: ModelShield: Adaptive and Robust Watermark Against Model Extraction Attack
- Blog: Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
- Blog: A Character-Centric Creative Story Generation via Imagination
- Blog: Improving Classification Performance With Human Feedback: Label a few, we label the rest
- Blog: Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
- Blog: Zero-Shot Vision Encoder Grafting via LLM Surrogates
- Blog: What do Geometric Hallucination Detection Metrics Actually Measure?
- Blog: EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
- Blog: Extracting and Summarizing Evidence of Suicidal Ideation in Social Media Contents Using Large Language Models
- Blog: How Deeply Do LLMs Internalize Human Citation Practices? A Graph-Structural and Embedding-Based Evaluation
- Blog: Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features
- Blog: PATCH! Psychometrics-AssisTed BenCHmarking of Large Language Models against Human Populations: A Case Study of Proficiency in 8th Grade Mathematics
- Blog: Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
- Blog: SPO: Self Preference Optimization with Self Regularization
- Blog: DSCD: Large Language Model Detoxification with Self-Constrained Decoding
- Blog: From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages
- Blog: Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
- Blog: Rank-Without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
- Blog: Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation
- Blog: Arabic Train at NADI 2024 shared task: LLMs’ Ability to Translate Arabic Dialects into Modern Standard Arabic
- Blog: Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic
- Blog: Are the Reasoning Models Good at Automated Essay Scoring?
- Blog: Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
- Blog: Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- Blog: Can LLMs Be Efficient Predictors of Conversational Derailment?
- Blog: Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
- Blog: Integrating Rules and Semantics for LLM-Based C-to-Rust Translation
- Blog: Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
- Blog: Adapting Self-Supervised Learning for Computational Pathology
- Blog: The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs
- Blog: ARG2ST at CQs-Gen 2025: Critical Questions Generation through LLMs and Usefulness-based Selection
- Blog: Efficient Reasoning with Hidden Thinking
- Blog: Less is more: Towards green code large language models via unified structural pruning
- Blog: SKRAG: A Retrieval-Augmented Generation Framework Guided by Reasoning Skeletons over Knowledge Graphs
- Blog: Sparse Auto-Encoder Interprets Linguistic Features in Large Language Models
- Blog: LoRAM: Low-Rank Adaptation of Large Language Models on Manifold
- Blog: Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models
- Blog: Psychologically-Inspired Causal Prompts
- Blog: A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look
- Blog: What Counts Underlying LLMs’ Moral Dilemma Judgments?
- Blog: What Causes Knowledge Loss in Multilingual Language Models?
- Blog: CoRT: Code-integrated Reasoning within Thinking
- Blog: Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
- Blog: Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs
- Blog: Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems
- Blog: Label Representations in Modeling Classification as Text Generation
- Blog: Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
- Blog: Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
- Blog: PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Blog: Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study
- Blog: LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation
- Blog: Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers
- Blog: CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
- Blog: Persona Prompting as a Lens on LLM Social Reasoning
Showing 60 of 452 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_limited_model_scope_cross_architecture_v_135cd5bb,
title = {limited model scope (cross-architecture validation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/limited-model-scope-cross-architecture-validation/rdr_135cd5bbd34b458ba5169adc6b183014},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_limited_model_scope_cross_architecture_v_135cd5bb_v1,
title = {limited model scope (cross-architecture validation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/limited-model-scope-cross-architecture-validation/rdr_135cd5bbd34b458ba5169adc6b183014/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}