SIMposium 2025: Dr. Ameeta Agrawal will join the panel “The GenAI Shift — From Experiments to Enterprise Impact,” sharing insights on scaling generative AI responsibly while addressing challenges of governance, bias, and ethics in real-world applications on Nov 13th, Portland OR.

Paper Updates

• EMNLP 2025: Amber Shore presented Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs.
• EMNLP 2025: Francielle Vargas and Jackson Trager presented our collaborative work with Dr. Ameeta Agrawal on multi-hop hate speech detection and explanation - MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Hate Speech Multi-hop Explanation.
• ICDM 2025: Yufei Tao will present Lost-in-the-Later: Framework for Quantifying Contextual Grounding in Large Language Models at the Workshop on Grounding Documents with Reasoning, Agents, Retrieval, and Attribution @ ICDM 2025.
• AAAI 2025 Fall Symposium Series: (Nov 6–8, Arlington VA) Our paper Towards Personalized Explanations for Health Simulations: A Mixed-Methods Framework for Stakeholder-Centric Summarization by Philippe Giabbanelli and Ameeta Agrawal will be presented.

Congratulations to Dr. Ameeta Agrawal! Dr. Ameeta Agrawal has been named a 2025–2027 Wedge Vision Professor in the Maseeh College of Engineering and Computer Science, Portland State University, which includes two years of discretionary funding.

Accepted at the Findings of IJCNLP-AACL 2025

• CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences (Rhitabrat Pokharel, Yufei Tao, Ameeta Agrawal)
• MTQ-Eval: Multilingual Text Quality Evaluation for Language Models (Rhitabrat Pokharel, Ameeta Agrawal)

Paper at EPJ Data Science: Dr. Agrawal’s paper, Understanding the Role of Sentiment and Emotion for Predicting Forced Displacement, was recently published in EPJ Data Science. Congratulations!

CCSC-NW: Dr. Agrawal delivered a keynote on “LLMs and the Shifting Landscape of CS Education” during CCSC-NW at Saint Martin’s University College of Business, Engineering, and Technology, sparking great discussion on rethinking computer science education.

CETI Event: A huge thank-you to Nandini R. for hosting such an incredible convening at CETI and to all the amazing panelists and audience members for sharing their insights. We’re grateful to be part of such a dynamic community that continues to push the boundaries of building (with) AI (with Ekata Mitra and Yufei Tao).

Invited Talk: On September 13, Prof. Agrawal delivered an invited talk at the AI Institute, Thinking with Machines, hosted by CETI, a local non-profit dedicated to fostering collaborative conversation and experiential learning.

Presented at NeSy 2025: Sina Bagheri Nezhad and Ameeta Agrawal presented their paper Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks at NeSy 2025 on September 10 in Santa Cruz, California. Look out for updates on their presentation and experiences in our next issue!

ACL 2025: Russell Scheinberg and Ameeta Agrawal attended ACL 2025 in Vienna, Austria, along with University of Miami collaborator So Young Lee, where they presented their paper Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments.

Accepted at EMNLP 2025:

• Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs (Amber Shore, Russell Scheinberg, Ameeta Agrawal, So Young Lee).
• MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Hate Speech Multi-hop Explanations (Jackson Trager, Francielle Vargas, Diego Alves, Matteo Guida, Mikel K. Ngueajio, Flor Plaza-del-Arco, Yalda Daryanai, Farzan Karimi-Malekabadi, Ameeta Agrawal)

Presented at ISPE 2025: Andy Dang (PSU/Eli Lilly) presented Benchmarking Large Language Models and Optical Character Recognition to Enhance Network Meta-Analyses (Andy Dang, Ameeta Agrawal, Mingyang Shan).

Mentored NSF REU Program, 2025: Ameeta Agrawal and Ekata Mitra mentored Aniley Garcia at the Summer REU program at Portland State, focusing on code-switched text and bilingual generation in Spanglish.

Accepted at NeSy 2025: Our work “Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks” (Sina Bagheri Nezhad and Ameeta Agrawal) will be presented at NeSys 2025.

AI Seminar at Oregon State University: This spring, Dr. Ameeta Agrawal gave a compelling talk titled “Toward Bridging the Multilingual Divide in Language Technologies” at the OSU AI Seminar Series.

Rhitabrat Pokharel and Sina Bagheri Nezhad started their internships at Optum and ElastixAI respectively.

MS Graduation: Martha O. D. earned her M.S. at PSU with a thesis on “Model Explanations for Gender and Ethnicity Bias Mitigation in AI‑Generated Narrative”.

BS Honors Thesis: Eben Weisman completed his honors thesis titled “Investigating Key Structures in Protective Scenes for LLMs”.

Congrats to Sina on successfully defending his dissertation proposal!

“Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments” accepted at the Findings of ACL 2025.

Ameeta Agrawal, PhD, gave an invited talk on Building Inclusive Language Technologies at the “Value and Responsibility in AI Technologies conference” held at Gonzaga University on April 3-4.

Presented at NAACL 2025:

• Russell presented his work on Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs? [ So Young Lee, Russell Scheinberg, Amber Shore, and Ameeta Agrawal, PhD] at NAACL 2025.
• At the Cross-cultural NLP workshop hosted at NAACL, we presented Fair Summarization: Bridging Quality and Diversity in Extractive Summaries, NAACL 2025 Workshop on Cross-Cultural Considerations in NLP by Sina Bagheri Nezhad, Sayan Bandyapadhyay, and Ameeta Agrawal, PhD.

Rhitabrat Pokharel from our lab attended the AI Unlocked Workshop organized by the NAIRR Pilot in Denver, Colorado.

Papers Acceptances:

• CROSS: Analyzing the Trade-offs in Long-Context Cross-lingual Retrieval, ICLR 2025 Workshop on Foundation Models in the Wild by Nezhad et. al.
• Fair Summarization: Bridging Quality and Diversity in Extractive Summaries, NAACL 2025 Workshop on Cross-Cultural Considerations in NLP by Nezhad et. al.

At NAACL in Albuquerque, New Mexico, our lab will present the paper, “Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?” (Young Lee, Russell Scheinberg, Amber Shore, and Ameeta Agrawal, PhD)

Acceptance on SEAS workshop (AAAI-25): Rhitabrat Pokharel’s work got accepted, “The Impact of Model Scaling on Seen and Unseen Language Performance” (Rhitabrat Pokharel and Ameeta Agrawal, PhD)

A paper titled “The Impact of Model Scaling on Seen and Unseen Language Performance” accepted at SEAS workshop co-located with AAAI 2025.

Two papers accepted at COLING 2025 workshops.

Congrats to Russell and Amber for getting a paper accepted at PACLIC 2024.

Congrats, Amber! She has been selected for the 2024-2025 CLS Refresh program funded by the U.S. Department of State! She’ll receive Ukrainian tutoring this Spring.

A paper accepted at the Algorithmic Fairness through the Lens of Metrics and Evaluation (AFME) workshop @ NeurIPS 2024!

A paper accepted at EMNLP 2024 and another at MRL Workshop @ EMNLP 2024!

Excited to be part of NSF’s NAIRR Pilot with our project, Towards Understanding and Improving Multilingual Abilities of Large Language Models [NAIRR240158].

Amila successfully defended her MS thesis titled Automatic Measurement of Dialogue Engagingness in Multilingual Settings.

Two papers accepted at NAACL 2024 workshop (VarDial).

Our paper titled ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalness accepted at LREC-COLING 2024.

We’ll be presenting our work on efficient conversation modeling at Towards Ethical and Inclusive Conversational AI (TEICAI) Workshop @ EACL 2024.

Congratulations Aravind (and Prof. Agrawal) for the best paper award! The paper on Narrating Causal Graphs with Large Language Models was recently presented at HICSS 2024.

One Paper Accepted at Findings of EMNLP and another at MRL Workshop @ EMNLP 2023!

A warm welcome to the new PhD students: Amber Shore, Andy Dang, and Ellyn Ayton!

We’re grateful for two NSF grants on HNDS-R: Understanding Drivers of Trust in Cryptocurrency Using Big Data and Ethnographic Approaches and EAGER: Re-imagining the Role of Humans in Security Education.

Our paper titled All Translation Tools Are Not Equal: Investigating the Quality of Language Translation for Forced Migration accepted at DSAA 2023!

Four papers accepted at ACL 2023 workshops (*SEM, WASSA, SustaiNLP, and WOAH)!

Congratulations to Prof. Agrawal on winning the Graduate Advising and Mentoring Excellence Award!

Congratulations, Rhitabrat, on securing Dr. Abdul Qayum Endowed Graduate Fellowship!

Received a research grant from NSF [2246174]!

Join CoCo Lab’s Ideathon 2023 - ‘AI for Creative Storytelling’.

A new PhD student, Ekata Mitra, joined our lab.

An MS student, Amila Ferron, joined our lab.

Our paper on Re-assessing Evaluation Metrics for Summarization has been accepted at GEM at EMNLP 2022.

A new PhD student, Erik Conser, joined our lab.

A new PhD student, Sina Bagheri Nezhad, joined our lab.

Our paper on Diversity and Summarization accepted at COLING 2022.

A new PhD student, Aravind Inbasekaran, joined our lab.

A new PhD student, Russell Scheinberg, joined our lab.

Our paper on Unsupervised Knowledge Graph accepted at NAACL (DeepLoNLP) 2022.

Aaron Hudson successfully defended his MS thesis.

New PhD student, Yufei Tao, joined our lab.

Our paper on Sustainable Pretraining accepted at SustaiNLP at EMNLP 2021 (honorable mention for best paper award!).

Our paper accepted at SmartComp 2021 (wip).

Received a research grant from Cisco Research!

Kicked off a new monthly seminar series in collaboration with Applied Linguistics.

Looking for motivated and hard-working students to join our PortNLP lab.

PortNLP lab is launched.