activity
20152026
most citedWhat do you learn from context? Probing for sentence structure in contextualized word representations

139 citations · 242 across the 41 of their papers we have counts for

collaborators
Showing 2024Show all

8 papers · 1 filter

cs.CL20241 cited

LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error

Boshi Wang, Hao Fang, Jason Eisner +2

Tools are essential for large language models (LLMs) to acquire up-to-date information and take consequential actions in external environments. Existing work on tool-augmented LLMs…

cs.CL2024

TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning

Kate Sanders, Nathaniel Weir, Benjamin Van Durme

It is challenging for models to understand complex, multimodal content such as television clips, and this is in part because video-language models often rely on single-modality rea…

cs.CL2024

RORA: Robust Free-Text Rationale Evaluation

Zhengping Jiang, Yining Lu, Hanjie Chen +3

Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential…

cs.CL2024

Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic

Nathaniel Weir, Kate Sanders, Orion Weller +8

Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on br…

cs.CL2024

Streaming Sequence Transduction through Dynamic Compression

Weiting Tan, Yunmo Chen, Tongfei Chen +5

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dyn…

cs.CL2024

MultiMUC: Multilingual Template Filling on MUC-4

William Gantt, Shabnam Behzad, Hannah YoungEun An +4

We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Ara…