Papers by Dian Zhou

12 papers
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations (2024.naacl-long)

Copied to clipboard

Challenge: Sentence embeddings are typically learned to recognize the semantic relation between two text inputs.
Approach: They introduce a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
Outcome: The proposed model is able to produce contextual embeddings corresponding to different atomic propositions, i.e. semantic equivalence between propositions across different text sequences.
LiGen: Active Lipid Generation via a Molecular Language Model (2026.acl-long)

Copied to clipboard

Challenge: Lipid nanoparticles (LNPs) can deliver cargos to tumor and immune cells . traditional approaches rely on experimental screening and expert judgment .
Approach: They propose a method to generate lipid molecules efficiently and actively using deep learning.
Outcome: The proposed method outperforms baseline methods on multiple cell lines and achieves a 30% improvement over the current methods.
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Challenge: Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach: They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome: The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction (2025.findings-acl)

Copied to clipboard

Challenge: Large language models excel on a variety of reasoning benchmarks, but struggle to generalize to unseen questions due to over-reliance on memorized training examples.
Approach: They propose to identify a set of linear features in the model’s residual stream that govern the balance between genuine reasoning and memory recall.
Outcome: The proposed model can be manipulated to activate the most relevant problem-solving capabilities during answer generation.
Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience (2026.acl-long)

Copied to clipboard

Challenge: Existing verifiers operate on the surface text or on confidence proxies derived from token probabilities, which can be brittle.
Approach: They propose a training-free, non-parametric verifier that summarizes each reasoning trace by an activation delta and compares it to two class centroids computed from labeled experience.
Outcome: The proposed model improves selection and reranking on large and less-calibrated models.
Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing reinforcement learning methods rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions.
Approach: They propose a process reward model that rewards correct steps only when they detect errors . they propose VPPO, which rewards the correct prefix and an erroneous suffix .
Outcome: a new approach outperforms sparse-reward RL and prior PRM-guided baselines on Pass@1 and Pass@K . a process reward model (PRM) outperformed sparser-rebound RL on multiple reasoning benchmarks .
Attribute Alignment: Controlling Text Generation from Pre-trained Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Large language models can generate text with sentiment polarity or specific topics without changing the original model parameters.
Approach: They propose a method for controlling text generation by aligning disentangled attribute representations.
Outcome: The proposed method shows large performance gains while maintaining diversity and fluency.
WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach: They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome: The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .
MIDAS: A Dialog Act Annotation Scheme for Open Domain HumanMachine Spoken Conversations (2021.eacl-main)

Copied to clipboard

Challenge: Existing dialog act schemes are designed for human-human conversations, but are not suitable for automatic speech recognition.
Approach: They propose a dialog act annotation scheme for open-domain human-machine conversations . they collected 24K utterances from a large open- domain spoken conversation dataset .
Outcome: The proposed scheme achieves an F1 score of 0.79 on a 24K spoken conversation dataset.
End-to-End Chinese Speaker Identification (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods for speaker identification in texts are incomplete and introduce errors that propagate and seriously affect the final output.
Approach: They propose to use speaker identification (SI) in texts to identify the speaker(s) for each utterance in texts.
Outcome: The proposed model can achieve comparable or better than previous state-of-the-art methods on all public SI datasets for Chinese.
Gunrock: A Social Bot for Complex and Engaging Long Conversations (D19-3)

Copied to clipboard

Challenge: Gunrock is a speech-based social chatbot that can be used to understand complex sentences and have in-depth conversations.
Approach: They propose a system that allows users to understand complex sentences and have in-depth conversations in open domains.
Outcome: The proposed system produces longer sentences, which are directly related to user engagement (e.g., ratings, number of turns).
Dependency Parsing for Spoken Dialog Systems (D19-1)

Copied to clipboard

Challenge: Dependency parsing of conversational input can help to understand dialogs . currently available annotation schemes do not adapt well to spoken human-machine dialogs.
Approach: They propose an annotation scheme that extends Universal Dependencies guidelines to spoken dialogs.
Outcome: The proposed scheme disambiguates relationships between entities extracted from dialogs . it is better than existing models on public datasets and fine-tuned on ConvBank data .

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