LNLS @ ACL 2022

11 papers

Top Research Directions

The 13 research directions with LNLS @ ACL 2022 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Alignment Free Sequence Training with Connectionist Temporal Classification19.1%
2Benchmarking Explainable AI Using Verifiable Ground Truths19.1%
3Bridging the Few-Shot Generalization Gap19.1%
4Complexity Ordered Curriculum Learning for Logical Reasoning19.1%
5Evaluating the Faithfulness of Machine Learning Explanations19.1%
6Progressive Sequence Length Training19.1%
7Prompting Large Language Models for Zero Shot Inference19.1%
8Rationale-Augmented Classification19.1%
9Reconstructing Chronological Timelines from Non Linear Narratives19.1%
10Resolving Ambiguity in Natural Language Instructions for Robotic Agents19.1%
11Resolving Functional Ambiguity through Pragmatic Inference19.1%
12Specific to General Rule Induction19.1%
13Synthetic Pretraining for Real World Generalization19.1%

Download all directions as CSV

Institutions

Institutions credited by LNLS @ ACL 2022 papers: a paper credits every institution named in its affiliations, once. 11 institutions share 7 credited papers.

#InstitutionPapersShare
1New York University 342.9%
2Princeton University 228.6%
3Anthropic (United States) 114.3%
4Genentech 114.3%
5IBM Research - Thomas J. Watson Research Center 114.3%
6Stony Brook University 114.3%
7The University of Tokyo 114.3%
8Universitat Politècnica de València 114.3%
9University of North Carolina at Chapel Hill 114.3%
10University of Sussex 114.3%
11University of the Basque Country 114.3%

Download all institutions as CSV

About this data

Papers. LNLS @ ACL 2022 lists 11 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 7 of 11 papers (63.6%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-22 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “LNLS @ ACL 2022”, https://lacuna.tiptreesystems.com/venue/lnls-acl/2022.

Top Authors

AuthorPapers
Angelica Chen2
Ethan Perez2
Karthik R Narasimhan2
Robert D. Hawkins2
Thomas L. Griffiths2
Akihiro Kishimoto1
Alicia Parrish1
Ameet Deshpande1
Austin W. Hanjie1
Brenden Lake1
Chuang Gan1
Dorsa Sadigh1
Dylan Hadfield-Menell1
Harsh Trivedi1
Ishita Dasgupta1
Jason Phang1
Jérémy Scheurer1
Jon Ander Campos1
Jonathan D. Cohen1
Joshua B. Tenenbaum1

Impactful Papers

Papers from LNLS @ ACL 2022 that shaped research clusters.

Foundational

Papers

Title
Few-shot image classification by generating natural language rules
Finding Sub-task Structure with Natural Language Instruction
Learning from Natural Language Feedback
Linguistic communication as (inverse) reward design
QuExEnt: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning
Revisiting the Roles of “Text” in Text Games
Semantic Supervision: Enabling Generalization over Output Spaces
Shared Autonomy for Robotic Manipulation with Language Corrections
Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions
Using Natural Language to Guide Meta-Learning Agents towards Human-like Inductive Biases
When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data