Ximing Lu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Tailoring Self-Rationalizers with Multi-Reward Distillation.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning.

[BibT_eX]

[DOI]

Bill Yuchen Lin

Abhilasha Ravichander

Ximing Lu

Nouha Dziri

Melanie Sclar

Chandra Bhagavatula

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

In Search of the Long-Tail: Systematic Generation of Long-Tail Knowledge via Logical Rule Guided Search.

[BibT_eX]

[DOI]

CoRR, 2023

Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing.

[BibT_eX]

[DOI]

CoRR, 2023

Improving Language Models with Advantage-based Offline Policy Gradients.

[BibT_eX]

[DOI]

CoRR, 2023

Localized Symbolic Knowledge Distillation for Visual Commonsense Models.

[BibT_eX]

[DOI]

Jae Sung Park

Jack Hessel

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Faith and Fate: Limits of Transformers on Compositionality.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Generating Sequences by Learning to Self-Correct.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning.

[BibT_eX]

[DOI]

Abhilasha Ravichander

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

STEER: Unified Style Transfer with Expert Reinforcement.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Fusing Pre-Trained Language Models with Multimodal Prompts through Reinforcement Learning.

[BibT_eX]

[DOI]

Ronan Le Bras

Gunhee Kim

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022

End-to-End diagnosis of breast biopsy images with transformers.

[BibT_eX]

[DOI]

Medical Image Anal., 2022

SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization.

[BibT_eX]

[DOI]

CoRR, 2022

Reinforced Clarification Question Generation with Defeasibility Rewards for Disambiguating Social and Moral Situations.

[BibT_eX]

[DOI]

CoRR, 2022

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation.

[BibT_eX]

[DOI]

CoRR, 2022

Multimodal Knowledge Alignment with Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2022

NaturalProver: Grounded Mathematical Proof Generation with Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

QUARK: Controllable Text Generation with Reinforced Unlearning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Twist Decoding: Diverse Generators Guide Each Other.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

ProsocialDialog: A Prosocial Backbone for Conversational Agents.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

MERLOT RESERVE: Neural Script Knowledge through Vision and Language and Sound.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Generated Knowledge Prompting for Commonsense Reasoning.

[BibT_eX]

[DOI]

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

2021

On-the-Fly Controlled Text Generation with Experts and Anti-Experts.

[BibT_eX]

[DOI]

CoRR, 2021

On-the-Fly Attention Modularization for Neural Generation.

[BibT_eX]

[DOI]

Jackie Chi Kit Cheung

CoRR, 2021

Understanding Few-Shot Commonsense Knowledge Models.

[BibT_eX]

[DOI]

CoRR, 2021

MERLOT: Multimodal Neural Script Knowledge Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

Analysis of Regions of Interest and Distractor Regions in Breast Biopsy Images.

[BibT_eX]

[DOI]

Proceedings of the IEEE EMBS International Conference on Biomedical and Health Informatics, 2021

Analyzing Commonsense Emergence in Few-shot Knowledge Models.

[BibT_eX]

[DOI]

Proceedings of the 3rd Conference on Automated Knowledge Base Construction, 2021

Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models.

[BibT_eX]

[DOI]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts.

[BibT_eX]

[DOI]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

On-the-Fly Attention Modulation for Neural Generation.

[BibT_eX]

[DOI]

Jackie Chi Kit Cheung