Papers by Daniel Chen
TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for entity retrieval use mention boundaries but unstructured text . state-of-the-art methods struggle to retrieve rare entities for ambiguous mentions . |
| Approach: | They propose a method to jointly train bi-encoders on knowledge graph types and unstructured text for entity retrieval for open-domain tasks. |
| Outcome: | The proposed method improves retrieval of rare entities on Ambiguous Entity Retrieval sets while maintaining strong overall retrieval performance on open-domain tasks. |
Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge (2025.naacl-long)
Copied to clipboard
Li Zhou, Taelin Karidi, Wanlong Liu, Nicolas Garneau, Yong Cao, Wenyu Chen, Haizhou Li, Daniel Hershcovich
| Challenge: | Recent studies have highlighted the presence of cultural biases in Large Language Models (LLMs), yet lack a robust methodology to dissect these phenomena comprehensively. |
| Approach: | They propose a multilingual dataset centered on food-related cultural facts and variations in food practices. |
| Outcome: | The proposed model incorporates cultural context significantly and improves its ability to access cultural knowledge. |
Sequence-to-sequence AMR Parsing with Ancestor Information (2022.acl-short)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a graph that encodes the semantic meaning of a sentence. |
| Approach: | They propose several strategies to add important ancestor information into a Transformer Decoder. |
| Outcome: | The proposed methods improve performance for both AMR 2.0 and AMR 3.0 datasets and achieve new state-of-the-art results. |
Few-shot Learning with Multilingual Generative Language Models (2022.emnlp-main)
Copied to clipboard
Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov, Xian Li
| Challenge: | Large-scale generative language models such as GPT-3 are competitive few-shot learners. |
| Approach: | They train multilingual generative language models on a corpus covering a diverse set of languages and study their few- and zero-shot learning capabilities. |
| Outcome: | The proposed model outperforms GPT-3 on 171 out of 182 directions with 32 training examples and surpasses the official supervised baseline in 45 directions. |
Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking (2024.eacl-long)
Copied to clipboard
| Challenge: | Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates. |
| Approach: | They propose a framework to integrate Chinese geographic semantics into re-ranking pipelines. |
| Outcome: | The proposed framework improves on two Chinese benchmark datasets. |
NICE: Neural Image Commenting with Empathy (2021.findings-emnlp)
Copied to clipboard
Kezhen Chen, Qiuyuan Huang, Daniel McDuff, Xiang Gao, Hamid Palangi, Jianfeng Wang, Kenneth Forbus, Jianfeng Gao
| Challenge: | Emotion and empathy are examples of human qualities lacking in many human-machine interactions. |
| Approach: | They propose to generate images with human-generated comments with enhanced emotion and empathy while minimizing inappropriate or offensive outputs. |
| Outcome: | The proposed model generates more human-like and engaging image comments on two images with human-generated comments and human annotations while minimizing inappropriate or offensive outputs. |
RORA: Robust Free-Text Rationale Evaluation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing metrics rely on degree to which rationale supports a label, but they fail to evaluate rationales that inadvertently leak the label. |
| Approach: | They propose a RObust free-text RAtionale evaluation against label leakage that quantifies the new information supplied by a rationale to justify the label. |
| Outcome: | The proposed evaluation outperforms existing methods in evaluating human-written, synthetic, or model-generated rationales, particularly demonstrating robustness against label leakage. |
Re-evaluating the Need for Visual Signals in Unsupervised Grammar Induction (2024.findings-naacl)
Copied to clipboard
Boyi Li, Rodolfo Corona, Karttikeya Mangalam, Catherine Chen, Daniel Flaherty, Serge Belongie, Kilian Weinberger, Jitendra Malik, Trevor Darrell, Dan Klein
| Challenge: | Recent studies show multimodal inputs can improve grammar induction, but weak textual baselines are needed for training. |
| Approach: | They use a fixed grammar family to compare multimodal grammar induction methods . they find multimodal inputs can improve grammar induction by grounding textual inputs to the visual world . |
| Outcome: | The proposed model outperforms weaker baselines on four benchmark datasets. |
Pay More Attention to Relation Exploration for Knowledge Base Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches focus on entity representation and final answer reasoning, which results in limited supervision for this task. |
| Approach: | They propose a framework that utilizes relations to enhance entity representation and introduce additional supervision. |
| Outcome: | The proposed framework improves the F1 score on two benchmark datasets by 5.8% . it improves by 6.7% on WebQSP, better than state-of-the-art methods . |
Lightweight Transformers for Conversational AI (2022.naacl-industry)
Copied to clipboard
| Challenge: | Commercial dialogue systems typically require a small footprint and fast execution time, but recent trends are in the other direction, resulting in difficulties in model deployment. |
| Approach: | They build Transformer-based Language Models from scratch on large corpora of conversational data and compare their performance against BERT and other strong baselines on dialogue probing tasks. |
| Outcome: | The proposed model outperforms existing models on dialogue probing tasks and can be fine-tuned on a single consumer GPU card. |
Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Current knowledge is limited on whether cultural features can predict cross-cultural transfer learning success for subjective tasks. |
| Approach: | They advocate integration of cultural information into datasets and cultural adaptability . findings suggest cultural features can predict cross-cultural transfer learning success . |
| Outcome: | The findings suggest that cultural features can predict cross-cultural transfer learning success in OLD tasks. |
Talking Point based Ideological Discourse Analysis in News Events (2025.findings-acl)
Copied to clipboard
Nishanth Sridhar Nakshatri, Nikhil Mehta, Siyi Liu, Sihao Chen, Daniel Hopkins, Dan Roth, Dan Goldwasser
| Challenge: | Existing models of ideological discourse analysis fail to capture the key elements that shape real-world narratives and lack the ability to integrate contextual information required for understanding abstract ideological views. |
| Approach: | They propose a framework motivated by the theory of ideological discourse analysis to analyze news articles related to real-world events. |
| Outcome: | The proposed framework can generate ideology-specific viewpoints (partisan perspectives) it can be used to generate event snapshots, a visual way of interpreting event discourse. |
Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving (2025.findings-naacl)
Copied to clipboard
Botao Yu, Frazier N. Baker, Ziru Chen, Garrett Herb, Boyu Gou, Daniel Adu-Ampratwum, Xia Ning, Huan Sun
| Challenge: | Existing evaluations of large language models (LLMs) with tools are limited and qualitative . existing evaluations have been limited and only focus on 14 tasks focusing on compound synthesis. |
| Approach: | They propose to develop an enhanced chemistry agent over ChemCrow to improve chemistry problem solving by integrating tools into LLMs. |
| Outcome: | The proposed agent does not consistently outperform its base LLMs without tools on specialized chemistry tasks and general chemistry questions. |
Rewarding Coreference Resolvers for Being Consistent with World Knowledge (D19-1)
Copied to clipboard
Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Hershcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
| Challenge: | Unresolved coreference is a bottleneck for relation extraction systems . a state-of-the-art system may be able to infer the relation using distributional information about the phrase the Sunshine State, but is likely to have limited evidence for the decision that it is coreferential with Florida rather than with Skynyrd. |
| Approach: | They propose to forward coreference input to relation extraction system and reward them for producing triples that are found in knowledge bases. |
| Outcome: | The proposed approach improves over the state-of-the-art by forwarding their input to a relation extraction system and rewarding resolvers for producing triples that are found in knowledge bases. |
Contrast Sets for Stativity of English Verbs in Context (2022.coling-1)
Copied to clipboard
| Challenge: | Current methods for classifying verbs in context as dynamic or stative are limited to particular data sets. |
| Approach: | They apply contrast set methodology to classify verbs in context as dynamic or stative . they create nearly 300 contrastive pairs by perturbing test set instances just enough to change their labels . |
| Outcome: | The contrast set method is used to evaluate the performance of a model on a classifying task . the model performs worse on transformed examples than on human examples . |
Using LLM for Improving Key Event Discovery: Temporal-Guided News Stream Clustering with Event Summaries (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Using hierarchical Dirichlet processes, we characterize news articles associated with key events from news streams. |
| Approach: | They propose a generic framework for news stream clustering that analyzes the temporal trend of news articles to automatically extract the underlying key news events that draw significant media attention. |
| Outcome: | The proposed framework produces more coherent clusters based on event summaries . the proposed framework is a first step in a new field of news analysis . |
My Case, For an Adposition: Lexical Polysemy of Adpositions and Case Markers in Finnish and Latin (2022.lrec-1)
Copied to clipboard
| Challenge: | Polysemy between adpositions and case markers is high in casemarked languages . a singular adeposition can cover a wide range of semantic fields while occupying the same syntactic context. |
| Approach: | They propose to manually annotate adposition and case marker tokens in Finnish and Latin translations of Le Petit Prince. |
| Outcome: | The proposed method can be applied to Finnish and Latin translations of Le Petit Prince . it uses k-means clustering to group raw, contextualized BERT embeddings . |
PerspectroScope: A Window to the World of Diverse Perspectives (P19-3)
Copied to clipboard
| Challenge: | PerspectroScope is a web-based system that lets users query a discussion-worthy natural language claim . |
| Approach: | They propose a web-based system which lets users query a discussion-worthy natural language claim and extract and visualize various perspectives in support or against the claim. |
| Outcome: | The proposed system lets users query a discussion-worthy natural language claim and extract and visualize various perspectives in support or against the claim. |
Argument Mining for Review Helpfulness Prediction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Argumentational features have been shown to be promising indicators of product review helpfulness, but their utility has been limited due to the lack of resources and large-scale experiments investigating their utility. |
| Approach: | They present an argumentational argumentation model that annotates 878 Amazon reviews on headphones and uses it to evaluate argument quality. |
| Outcome: | The proposed model improves the state-of-the-art model under text-only and text-and-image settings. |
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have underscored their exceptional reasoning prowess with natural language understanding across a broad spectrum of tasks. |
| Approach: | They examine whether Large Language Models actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. |
| Outcome: | The proposed model improves reasoning performance while suppressing it leads to notable degradation. |
API-Assisted Code Generation for Question Answering on Varied Table Structures (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to table question answering have been limited to specific table structures. |
| Approach: | They propose a unified TableQA framework that uses Python as a querying language and few-shot prompting to translate NL questions into Python programs. |
| Outcome: | The proposed framework provides a unified representation for structured tables as multi-index Pandas data frames and uses Python as a powerful querying language to translate NL questions into Python programs. |
On the Impact of Cross-Domain Data on German Language Models (2023.findings-emnlp)
Copied to clipboard
Amin Dada, Aokun Chen, Cheng Peng, Kaleb Smith, Ahmad Idrissi-Yaghir, Constantin Seibold, Jianning Li, Lars Heiliger, Christoph Friedrich, Daniel Truhn, Jan Egger, Jiang Bian, Jens Kleesiek, Yonghui Wu
| Challenge: | Traditionally, large language models have been trained on general web crawls or domain-specific data. |
| Approach: | They present a German dataset and a dataset aimed at containing high-quality data to examine the importance of data diversity over quality. |
| Outcome: | The proposed model outperforms models trained on quality data on multiple downstream tasks. |
Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection (2022.naacl-main)
Copied to clipboard
| Challenge: | a recent study shows that current NLP models operate non-incrementally, causing unacceptable delays for the user. |
| Approach: | They propose a streaming BERT-based sequence tagging model that detects disfluencies in real-time . they train the model to decide whether to immediately output a prediction or wait for further context . |
| Outcome: | The proposed model produces accurate predictions sooner than baselines, with lower flicker . disfluencies hurt readability of ASR transcripts, erode model performance on downstream tasks . |
Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020.findings-emnlp)
Copied to clipboard
Matt Gardner, Yoav Artzi, Victoria Basmov, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hannaneh Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A. Smith, Sanjay Subramanian, Reut Tsarfaty, Eric Wallace, Ally Zhang, Ben Zhou
| Challenge: | Standard test sets for supervised learning evaluate in-distribution generalization but are misleading when a dataset has systematic gaps. |
| Approach: | They propose a more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data. |
| Outcome: | The proposed model performs significantly lower on contrast sets than on the original test sets—up to 25% in some cases. |
Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent Mining (2022.naacl-industry)
Copied to clipboard
| Challenge: | Existing approaches to clustering unlabeled utterances are based on transformerbased sentence embedding methods. |
| Approach: | They propose a semantic embedding approach that can be leveraged to identify clusters of utterances that correspond to unhandled intents. |
| Outcome: | The proposed approach can identify clusters of utterances that correspond to unhandled intents from a large collection of enterprise virtual assistant data using a multi-task softmax loss. |
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)
Copied to clipboard
Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou
| Challenge: | XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios . |
| Approach: | They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora. |
| Outcome: | The proposed dataset is labeled in English and includes only natural language understanding tasks. |
GAIA: A Fine-grained Multimedia Knowledge Extraction System (2020.acl-demos)
Copied to clipboard
Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski, Marjorie Freedman
| Challenge: | Open source knowledge extraction tools are used for many real-world applications, but there is no comprehensive system for KE. |
| Approach: | They propose a multimedia knowledge extraction system that takes multimedia data from various sources and languages as input and creates a coherent, structured knowledge base. |
| Outcome: | The system achieves top performance at the recent NIST TAC SM-KBP2019 evaluation. |
Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims (N19-1)
Copied to clipboard
| Challenge: | a number of fact checking techniques are used to identify and eliminate biases in text data. |
| Approach: | They propose to use search engines to expand and diversify a dataset of claims, perspectives and evidence to address a selection bias. |
| Outcome: | The proposed approach outperforms existing methods in a language understanding task. |
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys (2024.findings-eacl)
Copied to clipboard
| Challenge: | integrating cultural dimensions with dialogue encoding features can enhance the predictive accuracy and quality of dialogue agents. |
| Approach: | They propose to incorporate cultural dimensions into dialogue encoding features to enhance the predictive accuracy of dialogue agents. |
| Outcome: | The proposed model improves the accuracy and quality of dialogue predictions by incorporating cultural dimensions with dialogue encoding features. |
Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards (2025.emnlp-main)
Copied to clipboard
Jaehoon Yun, Jiwoong Sohn, Jungwoo Park, Hyunjae Kim, Xiangru Tang, Daniel Shao, Yong Hoe Koo, Ko Minhyeok, Qingyu Chen, Mark Gerstein, Michael Moor, Jaewoo Kang
| Challenge: | Large language models have shown promise in clinical decision making, but current approaches struggle to localize and correct reasoning errors at specific steps of the reasoning process. |
| Approach: | They propose a process reward modeling framework that leverages retrieval-augmented generation to verify each reasoning step against established medical knowledge bases. |
| Outcome: | The proposed model improves on five medical QA benchmarks and two open-ended diagnostic tasks by 13.50% on MedQA. |
Improving Instruct Models for Free: A Study on Partial Adaptation (2025.emnlp-main)
Copied to clipboard
Ozan Irsoy, Pengxiang Cheng, Jennifer L Chen, Daniel Preotiuc-Pietro, Shiyue Zhang, Duccio Pappadopulo
| Challenge: | Instruct models are deemed superior and more usable but can be eroded by instruction tuning . a recent study shows that instruct models are better at following instructions than base models . |
| Approach: | They scale down the strength of instruction tuning to improve model performance . they show that reducing instruction tuning results in material improvement . |
| Outcome: | The proposed model improves on a few-shot in-context learning benchmark . but it loses some degree of its in-training ability . |
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (2024.findings-acl)
Copied to clipboard
Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
| Challenge: | Recent studies show that malicious prompt instructions could solicit objectionable content from LLMs. |
| Approach: | They compare how state-of-the-art LLMs respond to malicious prompts in different languages . they find that LLM's generate unsafe responses more often when a prompt is written in a lower-resource language . |
| Outcome: | The proposed model can generate unsafe responses more often when a malicious prompt is written in a lower-resource language, and less irrelevant responses when written in lower-source languages. |
Symbolic Planning and Code Generation for Grounded Dialogue (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models excel at processing and generating text and code, but lack a grounded task-oriented dialogue system that can handle grounding. |
| Approach: | They propose a modular and interpretable grounded dialogue system that integrates a reader and planner to convert partner utterances into executable code and a symbolic planner to determine the next appropriate response. |
| Outcome: | The proposed system outperforms the existing state-of-the-art on a one-common dialogue task and improves task success in human evaluations from 56% to 69% in the most challenging setting. |