Research19h ago
Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction#Benchmarks#LLM
Hooshware
ESTABLISHING NEURAL LINK...
a
arXiv – Computation and Language
Academic and institutional AI research source.
newsTrust 92/100Actively monitored
Latest coverage
News and signals attributed to arXiv – Computation and Language, with links to Hooshware coverage and the original publication.
Research1d ago
Made in Hungary: Comments on the performance of generative language models#Language Models#Evaluation#Hungarian#Research
AI News1d ago
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits#LLM
Research2d ago
Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety#transportation safety#RAG#large language models#countermeasure recommendation
Research2d ago
Comment on arXiv:2607.01233: Survivorship Bias in Published-Paper Baselines for Research-Idea Distributions#arxiv#survivorship bias#llm research#evaluation
Research3d ago
Clinical Reasoning Under a Partially Observed Objective in Cone Beam CT Report Generation#clinical reasoning#cone beam computed tomography#medical imaging#report generation
Research3d ago
ShopEase: A Generative AI-Based Multi-Agent Framework for Intelligent Enterprise Customer Support Using Hybrid Retrieval-Augmented Generation#multi-agent#customer support#RAG#LLaMA
Research3d ago
One Size Does Not Fit All: Setting Inference Depth from the Questions a Deployment Actually Asks#transformer#inference#early-exit#language-models
Research4d ago
Automated Detection and Structuring of Social Tipping Point Evidence in Climate related Documents: A Modular AI Framework#Milvus#Llama 3.2 3B#climate change#NLP
AI News4d ago
DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events#Scenario#LLM#Release#Released
AI News1w ago
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations#LLM
AI News1w ago
On the Impact of Anonymization on the Performance of Large Language Models#GPT-4o#GPT-4o mini#AI#GPT
Research1w ago
Through the Looking Glass: Directly Reading and Writing Transformers#transformers#mechanistic-interpretability#neural-networks#research
Research1w ago
Reliability, validity, and diagnostic evidence for multi-model LLM short-answer scoring#DeepSeek#LLM#educational assessment#reliability
Research1w ago
Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities#Reinforcement Learning#Catalan#Large Language Models#Text Simplification
AI News1w ago
On Epistemic Diversity in Large Language Models#LLM
Agents1w ago
Evidence Integration in Large Language Models#AI Agents
AI News2w ago
Language, Language Models, and What We're Talking AboutResearch2w ago
BharatGather: A Culturally-Informed Benchmark Dataset for Misinformation and Fake News Detection in Indian Public Events#dataset#misinformation#benchmark#nlp
AI News2w ago
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation#AI#LLM