3 52 47

Victor Jotham Ashioya

ashioyajotham

https://ashioyajotham.github.io/

ashioyajotham
ashioyajotham

AI & ML interests

Hallucination in LLMs, AI Safety: alignment, red-teaming

Recent Activity

updated a dataset 2 days ago

ashioyajotham/CoT_Faithfulness_Dataset

published a dataset 2 days ago

ashioyajotham/CoT_Faithfulness_Dataset

updated a Space 3 months ago

ashioyajotham/medgemma-clinical-reasoning

View all activity

Organizations

None yet

Victor Jotham Ashioya

AI & ML interests

Recent Activity

Organizations

ashioyajotham 's collections 7

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

Teaching Large Language Models to Reason with Reinforcement Learning

How Far Are We from Intelligent Visual Deductive Reasoning?

Common 7B Language Models Already Possess Strong Math Capabilities

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data

RAFT: Adapting Language Model to Domain Specific RAG

An Introduction to Vision-Language Modeling

Large-Scale Automatic Audiobook Creation

Agents: An Open-source Framework for Autonomous Language Agents

PDFTriage: Question Answering over Long, Structured Documents

StarCoder: may the source be with you!

Stealing Part of a Production Language Model

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

Large-Scale Automatic Audiobook Creation

Agents: An Open-source Framework for Autonomous Language Agents

PDFTriage: Question Answering over Long, Structured Documents

StarCoder: may the source be with you!

Teaching Large Language Models to Reason with Reinforcement Learning

How Far Are We from Intelligent Visual Deductive Reasoning?

Common 7B Language Models Already Possess Strong Math Capabilities

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data

Stealing Part of a Production Language Model

RAFT: Adapting Language Model to Domain Specific RAG

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

An Introduction to Vision-Language Modeling