New England NLP Symposium

About The Meeting

The New England NLP (NENLP) workshop aims to bring together researchers from the New England and nearby regions, bringing together expertise in natural language processing, language models, and related areas. The workshop aims to provide a participatory environment where attendees from prestigious institutions can share and discuss their latest findings. NENLP will cover a comprehensive range of topics related to language technologies, including large language models, evaluation, interpretability, post-training and alignment, reasoning, and many more. The program will feature a blend of invited keynote speakers, selected oral presentations, interactive poster sessions, and an exciting panel discussion.

Accepted Work and Awards Announced! 🎉

Schedule

09:00 AM - 09:20 AM	Breakfast & Registration
09:20 AM - 09:30 AM	Opening Remarks (Arman Cohan, Host PI; Jeffrey Brock, Dean of Yale Engineering)
09:30 AM - 10:00 AM	Keynote 1: Yilun Du: "Constructing Generalizable Multimodal Models through Compositional Generation"
10:00 AM - 10:30 AM	Keynote 2: Alex Lew: "Language Model Probabilistic Programming"
10:30 AM - 10:40 AM	Coffee Break (10 mins)
10:40 AM - 11:10 AM	Keynote 3: Byron Wallace: "LLMs for healthcare: Risks and interpretability methods to (possibly) mitigate them"
11:10 AM - 11:40 AM	Keynote 4: He He: "How Transformers Search in Reasoning Tasks"
11:40 AM - 12:50 PM	Walk to 17 Hillhouse Avenue (HLH17) - Lunch Reception (lunch will be served)
12:50 PM - 02:00 PM	Poster Session and discussions
02:00 PM - 02:30 PM	Break and Walk to 53 Wall St Auditorium
02:30 PM - 03:00 PM	Keynote 5: Jason Weston: "Self-Improvement of LLMs"
03:00 PM - 03:30 PM	Keynote 6: Yoon Kim: "On the Future of Transformers"
03:30 PM - 04:20 PM	Oral presentations - 5 talks (10 min each, 9 min talk + 1 min transition)
04:20 PM - 04:40 PM	Short Break (20 mins)
04:40 PM - 05:40 PM	Panel Discussion
05:40 PM - 05:50 PM	Closing Remarks & Awards
05:50 PM - 06:50 PM	End-of-Day Social at 17 Hillhouse Avenue (HLH17) (snacks and drink available)

Call For Papers

We invite submissions for the NENLP 2025 meetup, a one-day event dedicated to exploring the latest developments in NLP research. We welcome submissions on all aspects of NLP. Some of them will be selected for oral presentations and the remaining will be presented as posters. We encourage submissions from rising researchers who are enrolled in graduate programs at universities located in the New England region.

Dates

Submission deadline: March 31, 2025, (AOE)
Registraion deadline: April 2, 2025, (AOE)
Notification: April 3, 2025, (AOE)
Event Date: April 11, 2025

Submission guidelines

Submissions can be a work in progress or already published work. The overall length of the extended abstract should not exceed 500 words.
Titles and abstracts should be submitted through the link by the submission deadline.

April 7, 2025 update: We have reached full capacity and are no longer accepting submissions or registrations. We regret that the wailist is also closed and no more registrations can be accepted.

Topics

We welcome contributions across a broad spectrum of topics, including but not limited to:

LLM Training Methods
- Pretraining
- Post-training
- Training algorithms
Evaluation of LLM-based Systems
- Benchmarks
- Evaluation paradigms
- Evaluation methodologies and frameworks
Safety and Alignment
- Alignment Training
- Alignment Data
- Reliability
- Explainability
- Robustness
Reasoning
- Mathematical Reasoning
- Logical Reasoning
- Commonsense Reasoning
- Real-world applications
Multimodal Foundation Models
- Training techniques
- Data and benchmarks
- New applications
LLM Agents
- Agent components
- Planning and decision-making
- Tool usage
- End-to-end agentic systems
Data-centric NLP
- Data collection for model training
- Contamination and bias in NLP data
- Synthetic data generation methods
- Data quality
Code Models
- Code generation and completion
- Code understanding and optimization
- Applications in software engineering
Interpretability
- Novel interpretability approaches
- Mechanistic interpretability
- Causal relationships in NLP models
- Visualization tools for interpretability
Human-centered NLP
- User experience and design
- Human-AI interaction
- Accessibility and inclusivity
Low-resource and Multi-lingual NLP
- Evaluation benchmarks
- Cross-lingual alignment
- Resource-efficient training techniques
Applications of LLMs to Other Domains
- Healthcare and medical applications
- Law and finance
- Creative industries and arts
- Scientific research
Theory
- Theoretical foundations of NLP
- Complexity and computation in language models
- Challenges and open problems
Ethical and Societal Impacts
- Bias and fairness mitigation
- Privacy-preserving techniques
- Societal impacts and ethical concerns

Accepted papers will be presented as posters, with a subset selected for oral presentations. The workshop will take place in person in New Haven. 1 - 2 Best Paper Awards with will be given to the top papers!

Previous meetups: NENLP 2024 (Brown), NENLP 2023 (UMass Lowell), NENLP 2022 (MIT)