Hadi Amiri

Assistant Professor of Computer Science at UMass Lowell. Language + Healthcare. Previously at MIT, Harvard, UMD College Park, NUS, and University of Tehran.

[Kennedy College of Sciences at UMass Lowell @KCSciences_UML]

UMass Lowell’s new Cyber Security Operations Center (Cyber SOC) will help protect local communities and businesses while training future cyber pros.

📸: Paul Bryce

[Jiali Cheng @ACL2026 (Looking for jobs) @jialicheng123]

🎉Glad to share our COLM 2026 poster presenting today on Mode Connectivity of Unlearning! Huge thanks to @Hi_Soumyadeep for helping us present it!🙌
🕓 Time: Thu, Oct 8, 4:40 PM – 6:30 PM PDT
📍 Poster Session 6, #118
🏛️ Location: Grand Ballroom
📄 Paper: https://t.co/QlvPdEi1lC

[Hadi Amiri @amirieb]

@boydgraber Congratulations, Jordan! SG & NTU are wonderful!

[Hadi Amiri @amirieb]

This work led by @jialicheng123 moves machine unlearning toward a more mechanistic understanding of why some examples, features, or concepts are easier or harder to remove. Today at 2pm PTD:

[Jiali Cheng @ACL2026 (Looking for jobs) @jialicheng123]

Excited that our #ACL2026 paper with zihengchen, @_cagarwal, @amirieb on Measuring Unlearning Difficulty with MechInterp!

Time: Sun July 5, 14:00-15:30, Poster Session B
Location: Grand Hall

Looking forward to connecting with everyone!

https://t.co/kJn98SiTUM

[Hadi Amiri @amirieb]

Honored and grateful! Many thanks to the NSF, UMass Lowell, KCS, Miner school, mentors, collaborators, colleagues, and students for their support and inspiration.

[Kennedy College of Sciences at UMass Lowell @KCSciences_UML]

Please join us in congratulating Asst. Prof. Hadi Amiri (Miner School of Computer & Information Sciences) on his NSF Career Award! Well-deserved! @amirieb

[sijia.liu @sijialiu17]

See our MSU–IBM joint work on reasoning model “unlearning” presented at @emnlpmeeting, showcasing how unlearning can be leveraged to sanitize sensitive reasoning traces and enhance model safety.

[uclanlp @uclanlp]

We’ve been running the UCLA NLP Seminar for a while now and realized it’s a waste not to share these amazing talks more broadly.
So here’s our YouTube channel now!
🎥 Watch and subscribe to our channel for past and upcoming sessions:
👉 https://t.co/dbGIRMAAS4
#AI #UCLANLP

[Dan Jurafsky @jurafsky]

Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: https://t.co/pjfZsYxSk0

[Hadi Amiri @amirieb]

amazing talk by Robert Waldinger on what makes a good life? https://t.co/TsxTrnF4aq and a unique dataset! https://t.co/4bWMW7BS3y

[Hadi Amiri @amirieb]

EqualizeIR: Mitigating Linguistic Biases in Retrieval Models with @jialicheng123. We show that IR models are biased by the ling. complexity of queries, and introduce 4 types of weak learners to build robust retrievers. https://t.co/opM47RHn5N
#NLProc #NAACL2025

[Hadi Amiri @amirieb]

Today (4/25, 11am EST)! In our final CS Colloquium of this series, @msurd shares how combining symbolic rules with neural models leads to more explainable information extraction. #NLP #ExplainableAI @KCSciences_UML @uarizona
see details👉 https://t.co/oBxm1HYaq5

[Jessy Li @jessyjli]

Thank you so much @amirieb for hosting, amazing visit 🤗
New papers discussed:
QUDsim (discourse similarity): https://t.co/xqvbDvH5v0
Information salience in LLMs: https://t.co/Vi1XGJM4ZZ

[Hadi Amiri @amirieb]

This morning we had the pleasure of learning from @jessyjli about how LLMs model curiosity, discourse coherence, and information salience.👉 https://t.co/oBxm1HYaq5
#Linguistics #Discourse #NLP #LLMs
@KCSciences_UML @UT_Linguistics @UTAustin

[Hadi Amiri @amirieb]

Can LLM reason reliably? Join our CS colloquium with Greg Durrett (@gregd_nlp) on Specializing LLMs for Reliability: hallucination, model interpretation, and building reliable AI systems.
Today, 11:00am ET! Details 👉 https://t.co/oBxm1HYaq5
@KCSciences_UML @UTAustin #AI #NLP

[Hadi Amiri @amirieb]

We were honored to host Prof. Jiawei Han for an inspiring talk on integrating knowledge graphs with LLMs to accelerate theme-driven scientific discovery. (4/5, 11AM) @dmguiuc @KCSciences_UML
👉 https://t.co/oBxm1HYaq5

[Hadi Amiri @amirieb]

@RTomMcCoy thank you again for the wonderful talk, Tom.

[Hadi Amiri @amirieb]

Today (3/28, 11am EST) in our CS Colloquium @RTomMcCoy discusses how LLMs generalize beyond their training data and where they fall short! @KCSciences_UML @YaleLinguistics #AI #LLM #NLP #ComputationalLinguistics
👉 https://t.co/oBxm1HYaq5

[Hadi Amiri @amirieb]

@sijialiu17 Congratulations, Sijia!

[Hadi Amiri @amirieb]

LLMs for healthcare: Today in our CS colloquium @byron_c_wallace discusses the promises and perils of LLMs in medicine--from bias & hallucinations to interpretability! 11:00am ET! Details 👉 https://t.co/oBxm1HYaq5
@KCSciences_UML @KhouryCollege
#AI #LLMs #HealthcareAI #NLP

[Google AI @GoogleAI]

Introducing an advanced Articulate Medical Intelligence Explorer (AMIE), which goes beyond diagnosis towards treating and managing disease over time, matching clinician performance on multi-visit consultations in a study with patient actors. Learn more at https://t.co/39pfZJVaaM