| Aditya Yedetore |
Boston University |
Semantic Training Signals Promote Hierarchical Syntactic Generalization in Neural Networks |
| Alex Gu |
MIT |
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution |
| Alexis Ross |
MIT |
Toward In-Context Teaching |
| Alyssa Loo |
Brown University |
On The Heuristics of Transformer Models on Negation Tasks |
| Andi Peng |
MIT |
Preference-Conditioned Language-Guided Abstraction |
| Anton Kovalev |
UMass Lowell |
Entropy-based LLM Knowledge Probing |
| Benjamin Lipkin |
MIT |
LINC: Logical Inference via Neurosymbolic Computation |
| Catherine Chen |
Brown University |
Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models |
| Hayley Ross |
Harvard University |
When is a fake concert still a concert? A study of adjective-noun composition in LLMs |
| Jack Merullo |
Brown University |
Talking Heads: Communication Across Layers in Transformer Language Models |
| Koyena Pal |
Northeastern University |
Model Lakes |
| Linlu Qiu |
MIT |
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement |
| Lucas Torroba Hennigen |
MIT |
Towards Verifiable Text Generation with Symbolic References |
| Megan Wei |
Brown University |
Do music generation models understand music theory? |
| Namrata Shivagunde |
UMass Lowell |
Deconstructing In-Context Learning: Understanding Prompts via Corruption |
| Nihal Nayak |
Brown University |
Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation |
| Nikhil Prakash |
Northeastern University |
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking |
| Pratyusha Sharma |
MIT |
The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction |
| Ruochen Zhang |
Brown University |
Multilingual Large Language Models Are Not (Yet) Code-Switchers |
| Sanjana Ramprasad |
Northeastern University |
Examining hallucinations in summarization via model introspection |
| Shannon Shen |
MIT |
Learning to Decode Collaboratively with Multiple Language Models |
| Sherin Muckatira |
UMass Lowell |
Emergent Abilities in Reduced-Scale Generative Language Models |
| Simeng Han |
Yale University |
FOLIO: Natural Language Reasoning with First-Order Logic |
| Tassallah Amina Abdullahi |
Brown University |
Improving Zero-Shot Text Classification through Retrieval-based Query Reformulation |
| Tian Yun |
Brown University |
mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? |
| Vijeta Deshpande |
UMass Lowell |
LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data |
| William Merrill |
NYU |
The Illusion of State in State-Space Models |
| Yong Zheng-Xin |
Brown University |
LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons |
| Zhaofeng Wu |
MIT |
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks |
