I work on open, reliable LMs: augmented LMs & agents (RAG, tool use, deep research), safety (hallucinations, copyright), and AI for science, code & multilinguality & open to bold new ideas!
FAQ in 
I’m on the job market this year!
I’m completing my Ph.D. (2025), where I identify and tackle key LLM limitations like hallucinations by developing new models—Retrieval-Augmented LMs—to build more reliable real-world AI systems. Learn more in the thread! 
: arxiv.org/abs/2310.11511
: selfrag.github.io arxiv.org/abs/2211.09260
Can we train a single search system that satisfies our diverse information needs?
We present 𝕋𝔸ℝ𝕋 
the first multi-task instruction-following retriever trained on 𝔹𝔼ℝℝ𝕀 
, a collections of 40 retrieval tasks with instructions! 1/N
while keeping the original LM *frozen* 
[1/9]
Paper : homes.cs.washington.edu/~akari/papers/
tinyurl.com/2sdeuupn
github.com/AlexTMallen/ad
We all complain about LLM "hallucinations", but what are they? We study Automatic Fine-grained Hallucination Detection, with a novel taxonomy, a benchmark, and a 7B LM, surpassing ChatGPT in hallucination detection and editing
fine-grained-hallucination.github.io
arxiv.org/abs/2401.06855
1/7
Can LLMs perform well across languages?
Our new benchmark BUFFET enables a fair eval. for few-shot NLP across languages in scale.
Surprisingly, LLMs+Incontext learning (incl. ChatGPT) are often outperformed by much smaller fine-tuned LMs
tinyurl.com/BuffetFS
forbes.com/30-under-30/20
More updates soon… 
1/7
