Papers by Zijing Shi

10 papers
Spiral of Silence in Large Language Model Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing theories of Spiral of Silence do not apply to large language models .
Approach: They propose an evaluation framework for examining SoS in large language models . they consider four controlled conditions that vary the availability of "History" and "Persona" signals .
Outcome: The proposed framework examines the SoS-like dynamics in large language models . it shows that history and persona together produce strong majority dominance .
Why Do More Experts Fail? A Theoretical Analysis of Model Merging (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for model merging struggle to maintain performance gains as the number of merged models increases.
Approach: They propose a Reparameterized Heavy-Tailed method to extend the merged model’s coverage and enhance performance.
Outcome: The proposed method extends the merged model’s coverage and enhances performance on 19 benchmarks, including knowledge-intensive and general-purpose tasks.
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models (2023.acl-long)

Copied to clipboard

Challenge: Existing studies on social biases in language models have focused on only English.
Approach: They propose to use a Chinese dataset for bias evaluation and mitigation of Chinese conversational language models.
Outcome: The proposed dataset includes under-explored bias categories, such as ageism and appearance biases, which received less attention in previous studies.
Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)

Copied to clipboard

Challenge: Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China.
Approach: They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform.
Outcome: The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower.
Benchmarking Web Agent Safety under E-commerce Deceptive Interfaces (2026.acl-long)

Copied to clipboard

Challenge: Existing web agents are highly susceptible to multiple classes of deceptive interfaces, but they are not designed to mitigate these failures.
Approach: They propose a lightweight plugin framework that allows controlled injection of deceptive interface patterns into existing web environments.
Outcome: The proposed framework enables controlled injection of deceptive interface patterns into web environments.
Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies (2025.naacl-long)

Copied to clipboard

Challenge: Existing household robots are inability to recognize potential problems or dangers in home environments.
Approach: They propose a task of creating anomaly scenarios using generative models instead of manually labeled data to build simulated environments.
Outcome: The proposed framework outperforms existing models in terms of task description and scene diversity.
Self-imitation Learning for Action Generation in Text-based Games (2023.eacl-main)

Copied to clipboard

Challenge: Text-based games are situated systems where the game agents observe textual descriptions, and generate textual commands to interact with the environment.
Approach: They propose a confidence-based self-imitation model to generate action candidates for the RL agent by exploiting past valuable trajectories to adapt a pre-trained language model towards a target game.
Outcome: The proposed model performs well in multiple challenging games.
Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning (2026.acl-long)

Copied to clipboard

Challenge: Parameter-Efficient Fine-Tuning (PEFT) is an alternative to Full-Parameter Fine-tuning, but its effectiveness on complex tasks such as reasoning and instruction-following remains unclear.
Approach: They propose to use PEFT to reduce the number of trainable parameters while freezing the weights of LLMs.
Outcome: The proposed methods perform well on standard tasks, but weaknesses on complex and adversarial settings call for new directions beyond current paradigms.
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance.
Approach: They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation.
Outcome: The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs.
More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies on bias dataset construction and mitigation focus on one demographic group . in real-world applications, there are more than two demographic groups at risk of the same bias.
Approach: They propose to analyze and reduce biases across multiple demographic groups using a multi-demographic bias dataset.
Outcome: The proposed method can mitigate biases among multiple demographic groups effectively, the authors show .

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