Papers by Charles Chen
Task-Oriented Dialogue as Dataflow Synthesis (2020.tacl-1)
Copied to clipboard
Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H. Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov
| Challenge: | Existing approaches to task-oriented dialogue represent dialogue state as a dataflow graph . microsoft's SMCalFlow dataset features complex dialogues about events, weather, places, and people . |
| Approach: | They propose a dataflow graph-based dialogue agent that maps each user utterance to a program that extends this graph. |
| Outcome: | The proposed framework improves representability and predictability in natural dialogues . it uses dataflow graphs and metacomputation to map user intents to a program . |
Context Dependent Semantic Parsing over Temporally Structured Data (N19-1)
Copied to clipboard
| Challenge: | Existing semantic parsing tools only allow for natural language interactions, but the graphical interface could be improved significantly. |
| Approach: | They propose a semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. |
| Outcome: | The proposed architecture outperforms standard sequence generation baselines and achieves sequence-level accuracy of 88.7% on artificial data and 74.8% on real data. |
Constrained Language Models Yield Few-Shot Semantic Parsers (2021.emnlp-main)
Copied to clipboard
Richard Shin, Christopher Lin, Sam Thomson, Charles Chen, Subhro Roy, Emmanouil Antonios Platanios, Adam Pauls, Dan Klein, Jason Eisner, Benjamin Van Durme
| Challenge: | Large pretrained language models excel at generating natural language, but they are not efficient for task specific semantic parsing. |
| Approach: | They propose to use large pretrained language models as few-shot semantic parsers . they paraphrase inputs into a controlled sublanguage resembling English . |
| Outcome: | The proposed model can generate surprisingly accurate models on multiple tasks with minimal code and data. |
Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-agent LLMs are prone to adversarial attacks because of constraints such as limited token bandwidth and latency between message delivery. |
| Approach: | They propose a permutation-invariant adversarial attack that optimizes prompt distribution across latency and bandwidth constraints to bypass distributed safety mechanisms within the system. |
| Outcome: | The proposed method outperforms conventional attacks by up to 7 on multiple models. |
PyCantonese: Cantonese Linguistics and NLP in Python (2022.lrec-1)
Copied to clipboard
| Challenge: | a limited number of Cantonese-specific datasets are available for PyCantones. |
| Approach: | They introduce PyCantonese, an open-source Python library for Cantonesi linguistics and natural language processing. |
| Outcome: | The proposed library is open-source and available for free for all purposes, including commercial ones. |
Guided K-best Selection for Semantic Parsing Annotation (2022.acl-demo)
Copied to clipboard
Anton Belyy, Chieh-yang Huang, Jacob Andreas, Emmanouil Antonios Platanios, Sam Thomson, Richard Shin, Subhro Roy, Aleksandr Nisnevich, Charles Chen, Benjamin Van Durme
| Challenge: | a prototype model trained on a small amount of data is not available, leading to limited prediction performance. |
| Approach: | They propose a human-in-the-loop process that generates a set of valid candidates and allows users to quickly traverse the set and filter incorrect parses. |
| Outcome: | The proposed process can be used to efficiently traverse the candidate set and select the correct parse, with minimal modification when necessary. |
Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation (2022.findings-acl)
Copied to clipboard
| Challenge: | a low-resource task-oriented semantic parser is limited by privacy requirements for unlabeled natural utterances. |
| Approach: | They propose a setup for low-resource task-oriented semantic parsing based on user interactions . they use structured canonical utterances, then simulating corresponding natural language to improve performance. |
| Outcome: | The proposed setup improves on a low-resource task-oriented semantic parser using utterances collected through user interactions. |
Distilling Script Knowledge from Large Language Models for Constrained Language Planning (2023.acl-long)
Copied to clipboard
Siyu Yuan, Jiangjie Chen, Ziquan Fu, Xuyang Ge, Soham Shah, Charles Jankowski, Yanghua Xiao, Deqing Yang
| Challenge: | Existing work exploits language models to plan for abstract goals of stereotypical activities, but leaves more specific goals with multi-facet constraints understudied. |
| Approach: | They propose an over-generate-then-filter approach to improve large language models on constrained language planning task by distilling a constrained script dataset. |
| Outcome: | The proposed approach improves the constrained language planning ability of large language models on constraint faithfulness and also in smaller LMs. |
Heterogeneous Recycle Generation for Chinese Grammatical Error Correction (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work in the field of grammatical error correction (GEC) rely on neural machine translation-based models. |
| Approach: | They propose a heterogeneous approach to Chinese grammatical error correction using NMT-based models, sequence editing models, and a spell checker. |
| Outcome: | The proposed model achieves state-of-the-art performance without data augmentation or changes in architecture . it adapts the ERRANT scorer to be able to score Chinese sentences . |
The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been focused on single-agent, white-box environments, but multi-agend systems (MAS) have a critical blind spot: supply chain vulnerabilities. |
| Approach: | They propose a black-box auditing framework that leverages an Evolutionary Algorithm to autonomously expose hidden threats. |
| Outcome: | The proposed framework achieves superior detection rates (up to 100% in specific configurations) and robustness across diverse architectures. |