June 20267

19Jun

Deer, Deities, and Dancing: Culturally Biased LLM Hallucination in Low-Resource Wixárika Translation

Henry Gagnier

19 Jun · Underline Science Inc. · Artificial Intelligence

—Open access

19Jun

Kyrgyz Text Normalization: A Comparative Study of Neural and Rule-Based Approaches

Adilet Baktiiarovich Metinov

19 Jun · Underline Science Inc. · Artificial Intelligence

—Open access

3Jun

A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis

Daniil Orel

3 Jun · Underline Science Inc. · Sociology and Political Science

—Open access

3Jun

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

Arman Bolatov Daniil Orel

3 Jun · Underline Science Inc. · Artificial Intelligence

—Open access

3Jun

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning

Daniil Orel

3 Jun · Underline Science Inc. · Artificial Intelligence

—Open access

3Jun

Processing Inconsistency Predicts Language Competence: LLM Evaluation Without Answer Labels on Turkic Languages

Ilya Galyukshev

3 Jun · Underline Science Inc. · Artificial Intelligence

—Open access

3Jun

Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan

Ayana Mussabayeva Daniil Orel

3 Jun · Underline Science Inc. · Safety Research

—Open access

March 20264

14Mar

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR

Henry Gagnier

14 Mar · Underline Science Inc. · Scripting language

—Open access

14Mar

Orthographic Robustness of Persian Named Entity Recognition Models

Henry Gagnier

14 Mar · Underline Science Inc. · Named-entity recognition

—Open access

6Mar

A Benchmark and Evaluation of Automated Language of Study Extraction from Computational Linguistics Publications

Henry Gagnier

6 Mar · Underline Science Inc. · Benchmark (surveying)

—Open access

6Mar

AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Daniil Orel

6 Mar · Underline Science Inc. · Information Systems

—Open access

Research Hub

Make Central Asian AI research visible, connected, and easier to discover.

Open research profile

June 20267

Deer, Deities, and Dancing: Culturally Biased LLM Hallucination in Low-Resource Wixárika Translation

Kyrgyz Text Normalization: A Comparative Study of Neural and Rule-Based Approaches

A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning

Processing Inconsistency Predicts Language Competence: LLM Evaluation Without Answer Labels on Turkic Languages

Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan

March 20264

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR

Orthographic Robustness of Persian Named Entity Recognition Models

A Benchmark and Evaluation of Automated Language of Study Extraction from Computational Linguistics Publications

AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Research Hub

June 20267

Deer, Deities, and Dancing: Culturally Biased LLM Hallucination in Low-Resource Wixárika Translation

Kyrgyz Text Normalization: A Comparative Study of Neural and Rule-Based Approaches

A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning

Processing Inconsistency Predicts Language Competence: LLM Evaluation Without Answer Labels on Turkic Languages

Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan

March 20264

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR

Orthographic Robustness of Persian Named Entity Recognition Models

A Benchmark and Evaluation of Automated Language of Study Extraction from Computational Linguistics Publications

AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Upcoming deadlines

New in the hub

Latest seminar

Research Hub