Papers by Zeming Chen

13 papers
RETAIL: Towards Real-world Travel Planning for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing travel planning systems assume users provide explicit queries, limiting their practical utility.
Approach: They propose a dataset RETAIL which supports decision-making for implicit queries while covering explicit queries.
Outcome: The proposed model achieves a 1.0% pass rate, suggesting real-world travel planning remains challenging.
Discovering Knowledge-Critical Subnetworks in Pretrained Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Pretrained language models encode implicit representations of knowledge in their parameters, but localizing these representations and disentangling them from each other remains an open problem.
Approach: They propose a masking scheme that can be applied to weights and neurons to discover such subnetworks.
Outcome: The proposed method can remove specific knowledge from models while minimizing adverse effects on the original model.
Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs (2024.acl-long)

Copied to clipboard

Challenge: Currently, language models struggle to generate commonsense inferences for complex tasks due to data scarcity and the difficulty of reasoning over multiple pieces of information.
Approach: They propose a dataset to generate commonsense inferences from commonsensible data . they use a commonsence knowledge graph to extract and form questions from existing commonseense knowledge graphs.
Outcome: The proposed dataset improves the ability of language models to reason about complex events without expensive human annotations.
Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding (2022.naacl-main)

Copied to clipboard

Challenge: Existing evaluation methods do not provide insight into how well a language model captures distinct linguistic skills essential for language understanding and reasoning.
Approach: They propose a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena using a set of datasets and an evaluation procedure for diagnosing how well a language model captures reasoning skills.
Outcome: The proposed model can diagnose model behavior and verify model learning quality.
DISCO: Distilling Counterfactuals with Large Language Models (2023.acl-long)

Copied to clipboard

Challenge: high-quality counterfactual data is scarce for most tasks and not easily generated at scale.
Approach: They propose a method for automatically generating high-quality counterfactual data at scale . they use a large general language model to generate phrasal perturbations and filter them .
Outcome: The proposed method is task-agnostic and can be applied to the task of natural language inference.
Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge (2026.eacl-long)

Copied to clipboard

Challenge: Existing benchmarks for analyzing the performance of Large Language Models (LLMs) focus on single knowledge updates and fact recall, but do not consider how these updates affect downstream reasoning.
Approach: They propose a benchmark to study how LLMs propagate new knowledge when it conflicts with the model's parametric knowledge.
Outcome: The proposed benchmark compared models with no updated facts to show that the new methods worsen performance and improve reasoning performance.
Automatic Evaluate Dialogue Appropriateness by Using Dialogue Act (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluations of dialogue quality rely on human judgments, which are time-consuming, labor-intensive, prone to biases, and lacking objectivity.
Approach: They propose a method that utilizes the underlying patterns of dialogue act transitions to evaluate the appropriateness of chatbot responses.
Outcome: The proposed method proves that human judgments are time-consuming, labor-intensive, and lacking objectivity.
Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to GMNER use MLLMs as auxiliary tools, causing cumulative error propagation and a lack of rigorous cross-modal verification.
Approach: They propose a model that enforces structured cross-modal reasoning through Multi-style Reasoning Schema Injection and Constraint-guided Verifiable Optimization.
Outcome: The proposed model enforces structured cross-modal reasoning through multi-style Reasoning Schema Injection and Constraint-guided Verifiable Optimization.
Live-Aid: A Large-Scale Dialogue Dataset and Benchmark for Interleaved Multi-party Interactions in Live Streaming (2026.findings-acl)

Copied to clipboard

Challenge: Existing Multimodal Large Language Models struggle with dynamic interactions due to the scarcity of high-quality interleaved data.
Approach: They propose a large-scale interleaved live interaction Chinese dataset with human-annotated video responses.
Outcome: The proposed model can be used to evaluate live interactions in Chinese over 1,100 hours and 80,037 dialogue turns.
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent.
Approach: They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs.
Outcome: The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models.
NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning (2021.starsem-1)

Copied to clipboard

Challenge: Currently, symbolic and deep learning approaches to NLI are receiving less attention.
Approach: They propose a symbolic-based inference framework that integrates symbolic reasoning and semantic formalism to solve NLI tasks.
Outcome: The proposed framework improves accuracy on the NLI task and on the SICK and MED datasets.
Mitigating Label Biases for In-context Learning (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to categorize label biases in in-context learning (ICL) have not addressed all three types of label bias.
Approach: They propose a method that estimates a language model’s label bias using random in-domain words from the task corpus to categorize and detect label biases in ICL.
Outcome: The proposed method significantly improves the performance of GPT-J and GPT-3 on a wide range of tasks.
False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)

Copied to clipboard

Challenge: Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in Large Language Models’ internal representations.
Approach: They propose to use probing-based methods to study separability of malicious and benign inputs in LLMs' internal representations to detect harmful and benign content.
Outcome: The proposed methods show that they learn superficial patterns rather than semantic harmfulness.

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