32 citations · 154 across the 29 of their papers we have counts for
29 papers
Making Pre-trained Language Models both Task-solvers and Self-calibrators
Yangyi Chen, Xingyao Wang, Heng Ji
Pre-trained language models (PLMs) serve as backbones for various real-world systems. For high-stake applications, it's equally essential to have reasonable confidence estimations…
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
Zhenhailong Wang, Shaoguang Mao, Wenshan Wu +3
Human intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. In this work, we propose Solo P…
OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State Tracking
Xueqing Wu, Sha Li, Heng Ji
Open-vocabulary state tracking is a more practical version of state tracking that aims to track state changes of entities throughout a process without restricting the state space a…
C-PMI: Conditional Pointwise Mutual Information for Turn-level Dialogue Evaluation
Liliang Ren, Mankeerat Sidhu, Qi Zeng +3
Existing reference-free turn-level evaluation metrics for chatbots inadequately capture the interaction between the user and the system. Consequently, they often correlate poorly w…
Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
Chi Han, Qizheng He, Charles Yu +3
Probabilistic logical rule learning has shown great strength in logical rule mining and knowledge graph completion. It learns logical rules to predict missing edges by reasoning on…
Understanding the Effect of Data Augmentation on Knowledge Distillation
Ziqi Wang, Chi Han, Wenxuan Bao +1
Knowledge distillation (KD) requires sufficient data to transfer knowledge from large-scale teacher models to small-scale student models. Therefore, data augmentation has been wide…
Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy
Pengfei Yu, Heng Ji
Large Language Models~(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and co…
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models
Cheng Qian, Chi Han, Yi R. Fung +3
Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particul…
SciMON: Scientific Inspiration Machines Optimized for Novelty
Qingyun Wang, Doug Downey, Heng Ji +1
We explore and enhance the ability of neural language models to generate novel scientific directions grounded in literature. Work on literature-based hypothesis generation has trad…
Word Embeddings Are Steers for Language Models
Chi Han, Jialiang Xu, Manling Li +5
Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individua…
Understanding Emergent In-Context Learning from a Kernel Regression Perspective
Chi Han, Ziqi Wang, Han Zhao +1
Large language models (LLMs) have initiated a paradigm shift in transfer learning. In contrast to the classic pretraining-then-finetuning procedure, in order to use LLMs for downst…
ReFIT: Relevance Feedback from a Reranker during Inference
Revanth Gangi Reddy, Pradeep Dasigi, Md Arafat Sultan +4
Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), whi…
RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought
Tianci Xue, Ziqi Wang, Zhenhailong Wang +3
Large language Models (LLMs) have achieved promising performance on arithmetic reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting. However, LLMs face ch…
Paxion: Patching Action Knowledge in Video-Language Foundation Models
Zhenhailong Wang, Ansel Blume, Sha Li +5
Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the Action Dynamics Benchmark (ActionBench) containing two carefully d…
LeTI: Learning to Generate from Textual Interactions
Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand +1
Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning)…
Human-in-the-Loop Schema Induction
Tianyi Zhang, Isaac Tham, Zhaoyi Hou +12
Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extract…
Ensemble Transfer Learning for Multilingual Coreference Resolution
Tuan Manh Lai, Heng Ji
Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English h…
Retrieval-Augmented Generative Question Answering for Event Argument Extraction
Xinya Du, Heng Ji
Event argument extraction has long been studied as a sequential prediction problem with extractive-based methods, tackling each argument in isolation. Although recent work proposes…
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Chi Han, Hengzhi Pei, Xinya Du +1
Humans can classify data of an unseen category by reasoning on its language explanations. This ability is owing to the compositional nature of language: we can combine previously s…
A Close Look into the Calibration of Pre-trained Language Models
Yangyi Chen, Lifan Yuan, Ganqu Cui +2
Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1…
Language Model Pre-Training with Sparse Latent Typing
Liliang Ren, Zixuan Zhang, Han Wang +3
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only foc…
Code4Struct: Code Generation for Few-Shot Event Structure Prediction
Xingyao Wang, Sha Li, Heng Ji
Large Language Model (LLM) trained on a mixture of text and code has demonstrated impressive capability in translating natural language (NL) into structured code. We observe that s…
NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly
Yi R. Fung, Tuhin Chakraborty, Hao Guo +3
Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions. We introduce NormSage,…
CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval
Kung-Hsiang Huang, ChengXiang Zhai, Heng Ji
Fact-checking has gained increasing attention due to the widespread of falsified information. Most fact-checking approaches focus on claims made in English only due to the data sca…