Papers by Alan Guo
How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current studies evaluate LLMs on explicit false statements, overlooking how misinformation manifests subtly as unchallenged premises in real-world interactions. |
| Approach: | They propose to use EchoMist to analyze implicit misinformation from diverse sources . they also investigate two mitigation methods to enhance LLMs’ capability to counter implicit mis information. |
| Outcome: | The proposed model fails to detect false premises and generate counterfactual explanations. |
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 . |
Improved Instruction Ordering in Recipe-Grounded Conversation (2023.acl-long)
Copied to clipboard
| Challenge: | In this paper, we explore the task of instructional dialogue and focus on the cooking domain. |
| Approach: | They propose to explore two auxiliary subtasks to support response generation with improved instruction grounding by incorporating user intent and instruction state information into the model. |
| Outcome: | The proposed model lacks understanding of user intent and inability to track instruction state (i.e., which step was last instructed) incorporating user intent information helps the response generation model mitigate the incorrect order issue. |
Value-Agnostic Conversational Semantic Parsing (2021.acl-long)
Copied to clipboard
Emmanouil Antonios Platanios, Adam Pauls, Subhro Roy, Yuchen Zhang, Alexander Kyte, Alan Guo, Sam Thomson, Jayant Krishnamurthy, Jason Wolfe, Jacob Andreas, Dan Klein
| Challenge: | Existing models rely on rich representations of dialogue history that include all previously generated components of the output. |
| Approach: | They propose a model that abstracts over values to focus prediction on type- and function-level context. |
| Outcome: | The proposed model outperforms baseline models by 7.3% and 10.6% on SMCalFlow and TreeDST datasets. |
Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding (2024.acl-long)
Copied to clipboard
| Challenge: | Existing large language models struggle to capture some language styles without fine-tuning. |
| Approach: | They propose to meta-trained LLMs based on representative lexicons to recognize new styles they have not been fine-tuned on. |
| Outcome: | The proposed method improves zero-shot transfer across styles on 13 established and 63 novel tasks generated with LLMs. |
CARE: Multilingual Human Preference Learning for Cultural Awareness (2025.emnlp-main)
Copied to clipboard
| Challenge: | Language Models are tuned with human preferences to produce helpful responses, but the impact of preference tuning on the ability to handle culturally diverse queries remains understudied. |
| Approach: | They introduce a multilingual resource that contains culturally specific questions and 31.7k responses with human judgments. |
| Outcome: | The proposed model outperforms models with stronger initial cultural performance . the proposed model has gaps in the literature on culturally relevant data . |