Papers by Yiyang Li

22 papers
Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies on dialogue modeling use pre-trained language models to encode dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues.
Approach: They propose a bidirectional information decoupling network as a universal dialogue encoder which explicitly incorporates both the past and future contexts.
Outcome: The proposed model incorporates past and future contexts and can be generalized to a wide range of dialogue-related tasks.
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach: They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome: The proposed system enables more natural, robust, and human-aligned speech agents.
Model Composition for Multimodal Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities.
Approach: They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters.
Outcome: The proposed model retains the modal understanding capabilities of each original model.
Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use (2026.findings-eacl)

Copied to clipboard

Challenge: Illicit drug use among teens and young adults remains a public health concern . existing models ignore latent and interconnected structures among survey variables .
Approach: They propose a joint graph-language modeling framework to detect illicit drug use among TYAs . they use large-scale surveys such as the Youth Risk Behavior Survey and the National Survey on Drug Use and Health to analyze data .
Outcome: The proposed framework outperforms baseline models on YRBS and NSDUH datasets in predictive accuracy.
Universal Semantic Tagging for English and Mandarin Chinese (2021.naacl-main)

Copied to clipboard

Challenge: Existing approaches to generating semantic annotations for different languages are attracting more and more interest.
Approach: They propose to extend Universal Semantic Tagging to Mandarin Chinese and evaluate its performance.
Outcome: The proposed scheme is only tested in four Indo–European languages . accuracies are 92.7% and 94.6% for Chinese and English respectively .
Revisiting De-Identification of Electronic Medical Records: Evaluation of Within- and Cross-Hospital Generalization (2023.emnlp-main)

Copied to clipboard

Challenge: De-identification is a natural language processing task to detect and remove the protected health information (PHI) from electronic medical records (EMRs).
Approach: They propose a de-identification dataset comprising EMRs from three hospitals in China and use it to establish a benchmark for evaluating both within- and cross-hospital generalization.
Outcome: The proposed model with almost perfect within-hospital performance struggles when transferred across hospitals.
VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents (2026.findings-acl)

Copied to clipboard

Challenge: despite advances in multimodal conversational systems, current benchmarks lack comprehensive evaluation across key dimensions.
Approach: They propose a Chinese benchmark built exclusively on real human speech to fill this gap . they assess LALMs across three complementary axes: instruction following, knowledge understanding, robustness .
Outcome: VCB Bench assesses LALMs across three complementary axes: instruction following, knowledge understanding, and robustness . VCBM Bench provides reproducible and fine-grained framework for Chinese voice chat bots . results show significant performance disparities and offer tangible insights for future improvements .
Instance-level Randomization: Toward More Stable LLM Evaluations (2025.findings-emnlp)

Copied to clipboard

Challenge: Evaluations of large language models suffer from instability, where small changes of random factors can lead to drastic fluctuations of scores and even model rankings.
Approach: They propose an instance-level randomization method to reduce variance and improve fairness in evaluations by randomizing all factors that affect evaluation scores for every single instance.
Outcome: The proposed method reduces variance and improves fairness in model comparisons by using instance-level randomization.
SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph (2022.aacl-main)

Copied to clipboard

Challenge: Abstractive and extractive methods are used to condense long text into concise summaries while retaining essential information.
Approach: They propose to use paper structure to extract paper summaries from long text . they provide a large-scale dataset of COVID-19-related papers .
Outcome: The proposed framework generates more comprehensive and valuable summaries compared to previous work on COVID-19-related papers.
NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Diet plays a critical role in human health, but tailoring dietary reasoning to individual health conditions remains a challenge.
Approach: a new benchmark evaluates dietary reasoning using a national health survey data set.
Outcome: The NGQA benchmark evaluates dietary reasoning across three tasks using a set of question complexity settings and baseline models.
Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to sign language translation (SLT) assume video segments are directly mappable to spoken-language words.
Approach: They propose a reasoning-driven SLT framework that uses an ordered sequence of latent thoughts as an explicit middle layer between video and generated text.
Outcome: The proposed model improves coherence and faithfulness over existing gloss-free methods.
LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs (2025.acl-long)

Copied to clipboard

Challenge: TrickCatcher generates test cases that pass existing tests yet contain bugs . a recent study found that tricky bugs are not detected by test suites .
Approach: They propose an LLM-powered approach to generating test cases for uncovering bugs in plausible programs . they use a PUT and specification to generate program variants, an input generator and an Llm to construct test inputs .
Outcome: The proposed approach achieves recall, precision, and F1 scores that are 1.80, 2.65, and 1.66 . trickCatcher generates program variants based on the program under test and its specification .
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach: They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome: The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.
Pre-training Multi-party Dialogue Models with Latent Discourse Inference (2023.acl-long)

Copied to clipboard

Challenge: Existing studies have failed to scale up the pre-training process by putting aside unlabeled data . et al., 2019: multi-party dialogues are more difficult for models to understand since they involve multiple interlocutors resulting in interweaving reply-to relations and information flows.
Approach: They propose to treat discourse structures as latent variables and jointly infer them to pre-train a model that understands the discourse structure of multi-party dialogues.
Outcome: The proposed model outperforms baselines and achieves state-of-the-art results on multiple downstream tasks.
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Copied to clipboard

Challenge: Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach: They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome: The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.
Deep Span Representations for Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Challenge: Existing span-based NER systems shallowly aggregate token representations to span representations, causing performance degradations.
Approach: They propose a method that shallowly aggregates token representations to span representations . DSpERT produces span representation of deep semantics with weight initialization .
Outcome: The proposed model performs better than or competitive with state-of-the-art systems on six NER benchmarks.
Improving Factual Consistency in Abstractive Summarization with Sentence Structure Pruning (2024.lrec-main)

Copied to clipboard

Challenge: Abstractive summarization models suffer from factual inconsistency problem . post-editing methods focus on replacing suspicious entities, failing to modify incorrect content hidden in sentence structures.
Approach: They propose to use sentence pruning operation to correct possible errors . they propose to apply sentence pruning operations to the syntactic dependency tree .
Outcome: The proposed method improves factual consistency on the FRANK dataset compared with baselines . it is model-independent and can serve as the final step in ensuring factual consistentness.
Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to multimodal relation extraction ignore structural constraints and lack semantic expressiveness for fine-grained relation understanding.
Approach: They propose a framework that reformulates multimodal relation extraction as a retrieval task driven by relation semantics.
Outcome: The proposed framework achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.
Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models for multi-party dialogue machine reading comprehension focus on how to incorporate speaker information into the model, which is usually rare in real scenarios.
Approach: They propose to model speaker and key-utterances using self-supervised prediction tasks and capture salient clues in a long dialogue.
Outcome: The proposed method outperforms baseline models and state-of-the-art models on two benchmark datasets.
EM Pre-training for Multi-party Dialogue Response Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to pretrain large language models for dialogue response generation are difficult due to the lack of annotated addressee labels in multi-party dialogue datasets.
Approach: They propose an Expectation-Maximization approach that iteratively performs expectation steps to generate addressee labels and maximize a response generation model.
Outcome: The proposed method is based on two-party dialogues and multi-party dialogs.
Semantic-Preserving Adversarial Code Comprehension (2022.coling-1)

Copied to clipboard

Challenge: Existing studies on improving PrLMs for source code comprehension have not found a way to improve both sides of the trade-off between the two aspects.
Approach: They propose to use semantic-preserving code embeddings to find worst-case attacks while forcing the model to predict the correct labels under these worst cases.
Outcome: The proposed model can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code.
Removal of Hallucination on Hallucination: Debate-Augmented RAG (2025.acl-long)

Copied to clipboard

Challenge: erroneous or biased retrieval can mislead generation, compounding hallucinations.
Approach: They propose a framework that integrates multi-agent debates into retrieval and generation stages to improve retrieval reliability.
Outcome: The proposed framework improves retrieval reliability, reduces hallucinations and significantly improves overall factual accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations