Papers by Yuechen Wang

5 papers
Asking Clarification Questions in Knowledge-Based Question Answering (D19-1)

Copied to clipboard

Challenge: Existing clarification datasets with limited annotated examples do not address ambiguous phenomena.
Approach: They propose a dataset that allows users to ask clarification questions using open-domain examples.
Outcome: The proposed model achieves better performance than strong baselines and provides new challenges.
Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Copied to clipboard

Challenge: Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach: They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome: The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.
Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing weakly supervised methods for temporal language grounding lose the complexity of the video and the semantics of the sentence.
Approach: They propose a candidate-free framework for weakly supervised Temporal Language Grounding . they use a token-by-clip cross-modal semantic alignment module to learn alignment .
Outcome: The proposed framework achieves state-of-the-art on two widely-used benchmarks: ActivityNet-Captions, and DiDeMo.
Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)

Copied to clipboard

Challenge: Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input.
Approach: They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer .
Outcome: The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input .

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