Papers by Geng Tu

11 papers
How Does Selective Mechanism Improve Self-Attention Networks? (2020.acl-main)

Copied to clipboard

Challenge: Experimental results show that selective SANs outperform the standard SAN by paying more attention to content words that contribute to the meaning of the sentence.
Approach: They propose to implement selective SANs with a flexible Gumbel-Softmax to improve word order encoding and structure modeling.
Outcome: The proposed system outperforms the standard SANs on several representative NLP tasks including natural language inference, semantic role labelling, and machine translation.
Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)

Copied to clipboard

Challenge: Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK).
Approach: They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK.
Outcome: The proposed model outperforms state-of-the-art methods on two popular datasets.
OmniCode: A Benchmark for Evaluating Software Development Agents (2026.findings-acl)

Copied to clipboard

Challenge: popular coding benchmarks focus on narrowly scoped tasks such as competition programming and patch generation.
Approach: They propose a software engineering benchmark that aims to provide a broader set of tasks beyond code or patch generation.
Outcome: The proposed framework performs well on bug fixing for Python, test generation, code review fixing, and style fixing with popular agent frameworks such as SWE-Agent.
A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies in Emotion Recognition in Conversations (ERC) focus on capturing context-sensitive and speaker-sensitive dependencies, ignoring the unintended dataset biases of data.
Approach: They propose a training-free debiasing framework that extracts biases from the model by generating counterfactual utterances and contexts and mitigates them using simple yet empirically robust element-wise subtraction operations.
Outcome: Experiments on three public datasets show that the proposed framework improves generalization ability and fairness across different ERC models.
Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in Conversations (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on modeling context-sensitive dependencies and knowledge-sensitive dependences.
Approach: They propose a framework based on contrastive learning called CKCL to distinguish utterances for better vector representations.
Outcome: The proposed framework outperforms state-of-the-art models on four datasets.
Large Language Models as Reader for Bias Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: Traditional methods analyze text from the writer’s perspective, leaving the reader’s viewpoint underexplored.
Approach: They investigate whether large language models can be leveraged as readers for bias detection by generating reader-perspective comments.
Outcome: The proposed model performs comparable to GPT4's in detecting bias in media content.
Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to detect the knowledge boundary of Vision Large Language Models (VLLMs) are expensive and require indiscriminate retrieval to address questions that require real-time information or are knowledge-intensive.
Approach: They propose a method that fine-tunes a VLLM on an automatically constructed dataset for boundary identification.
Outcome: The proposed method reduces indiscriminate retrieval while maintaining or improving the performance of a VLLM on an automatically constructed dataset.
Probing Graph Decomposition for Argument Pair Extraction (2023.findings-acl)

Copied to clipboard

Challenge: Argument pair extraction (APE) aims to extract interactive argument pairs from two passages within a discussion.
Approach: They propose a method to extract interactive argument pairs from two passages . they propose to decompose the probing graph into four sub-graphs based on inter- and intra-passage perspectives .
Outcome: The proposed method improves on strong baselines on two benchmark datasets.
A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking (2026.findings-eacl)

Copied to clipboard

Challenge: Learning-style queries can reliably elicit harmful responses, highlighting a critical safety blind spot in modern LLMs.
Approach: They propose a new reframing paradigm that hides intention by learning from LLMs and uses 4 conceptual components to construct learning-style queries.
Outcome: The proposed framework achieves top attack success rates on most models and across malicious categories while maintaining high efficiency with concise prompts.
An Empirical Study on Multiple Knowledge from ChatGPT for Emotion Recognition in Conversations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing efforts in ERC focus on context- and speaker-sensitive dependencies, but lack of annotated data and high cost of obtaining such knowledge is a blank slate.
Approach: They propose a Multiple Knowledge Fusion Model to integrate multiple knowledge generated by Large Language Models (LLMs) they analyze the contribution and complementarity of this knowledge into the model.
Outcome: The proposed model integrates multiple knowledge generated by LLMs and analyzes its contribution and complementarity on three public datasets.
CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation (2025.acl-long)

Copied to clipboard

Challenge: Publicly available datasets can be used to evaluate performance of large language models . however, contamination of test data can artificially inflate model performance .
Approach: They propose a Contamination-resilient Evaluation strategy that updates data with real-world knowledge.
Outcome: The proposed evaluation strategy can be used to update datasets with real-world knowledge.

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