Papers by Geng Zhao

10 papers
Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing controllable dialogue generation models focus on single attribute and lack generalization capability to out-of-distribution multiple attribute combinations.
Approach: They propose a compositional generalization model that learns from seen attributes and generalizes to unseen combinations.
Outcome: The proposed model can learn from seen attribute values and generalize to unseen combinations.
Synergistic Interplay between Search and Large Language Models for Information Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Information retrieval (IR) is an indispensable technique for locating relevant resources from vast amounts of data.
Approach: They propose a framework that facilitates information refinement through synergy between RMs and LLMs.
Outcome: The proposed framework improves the performance of large-scale retrieval benchmarks on web searches and low-resource retrieval tasks.
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach: They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome: The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.
Cross-lingual Social Misinformation Detector based on Hierarchical Mixture-of-Experts Adapter (2025.coling-main)

Copied to clipboard

Challenge: a global trend of misinformation is affecting non-native speaker users who are more susceptible to misinformation on foreign social media platforms.
Approach: They propose a method to integrate sentiment analysis as an auxiliary task and a hierarchical routing strategy and expert-mask mechanism to enhance cross-lingual social misinformation detection.
Outcome: The proposed method improves cross-lingual social misinformation detection in non-native speakers with only monolingual social media histories.
FAA: Fine-grained Attention Alignment for Cascade Document Ranking (2023.acl-long)

Copied to clipboard

Challenge: Contemporary document ranking methods focus on transforming documents into passages to handle long inputs, but intensive query-irrelevant content may lead to harmful distraction and high query latency.
Approach: They propose a fine-grained attention alignment approach to jointly optimize a cascade document ranking model.
Outcome: Experiments on MS MARCO and TREC DL show that the proposed method is effective in document ranking tasks.
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective (2025.emnlp-main)

Copied to clipboard

Challenge: Large language model (LLM)-based embedding models surpass BERT and T5 on general-purpose text embeddable tasks.
Approach: They propose to adopt diffusion language models for text embeddings to overcome limitations in unidirectional attention used during autoregressive pre-training.
Outcome: The proposed model outperforms the existing LLM-based embedding model on reasoning tasks by 20% and 2% on traditional embeddable benchmarks.
Breaking the Attention Trap in Code LLMs: A Rejection Sampling Approach to Enhance Code Execution Prediction (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing research reveals significant performance bottlenecks in Code Execution tasks, which requires models to predict the execution results of given code snippets.
Approach: They propose to use attention cracking with rejection sampling to eliminate attention traps in training data and to conduct secondary training on the outputs generated by the fine-tuned model to mitigate negative impacts from manual data intervention.
Outcome: The proposed method eliminates the Attention Trap phenomenon in training data and conducts secondary training on the outputs generated by the fine-tuned model to mitigate negative impacts from manual data intervention.
Great Memory, Shallow Reasoning: Limits of kNN-LMs (2025.naacl-short)

Copied to clipboard

Challenge: Existing models trained on poor quality data have shown strong performance in language modeling and some downstream benchmarks.
Approach: They evaluate kNN-LMs on a diverse set of tasks and evaluate their performance.
Outcome: The proposed extension could improve on a variety of tasks, but it fails to perform on reasoning tasks that require integrating multiple pieces of information.
Multilingual Federated Low-Rank Adaptation for Collaborative Content Anomaly Detection across Multilingual Social Media Participants (2025.emnlp-main)

Copied to clipboard

Challenge: Recent developments in multilingual social media platforms (SNS) exacerbate new challenges in SNS content anomaly detection due to data islands and linguistic imbalance.
Approach: They propose a multilingual Federated LoRA based on SVD-based language-specific disentanglement of LoRA blocks and a local orthogonal tuning strategy to detect content anomalies.
Outcome: The proposed solution is superior in multilingual content anomaly detection while reducing multilingual knowledge conflicts and communication rounds.
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