Papers by Yaojie Zhang

14 papers
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Copied to clipboard

Challenge: Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach: They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome: The proposed approach mitigates language bias and consistently improves mRAG performance across languages.
MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Recent LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs and increasing compute cost and memory overhead.
Approach: They propose an agent framework that maintains a compact memory during multi-turn interactions.
Outcome: The proposed framework outperforms strong history-concatenation (ReAct-style) baselines on a range of public datasets while maintaining nearly constant token counts across multi-turn interactions.
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach: They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome: The proposed framework can be used to generate presentations with environmental observations.
Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to improve the reasoning performance of large language models rely on intuitive instance-level feedback, which limits the reasoning capabilities.
Approach: They propose a framework that pushes LLMs toward System-2-like critic capability by using a step-wise CoT reasoning paradigm and automatic construction of weak-supervision data without human annotation.
Outcome: The proposed model significantly improves task-solving performance by filtering out invalid solutions or iterative refinement.
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks focus on character-centric approach and fail to reflect real-world applications.
Approach: RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.
Outcome: RMTBench features 80 diverse characters and over 8,000 dialogue rounds.
Across Programming Language Silos: A Study on Cross-Lingual Retrieval-Augmented Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: Current research on large language models with retrieval-augmented code generation (RACG) has focused on single-language settings, leaving their cross-lingual effectiveness underexplored.
Approach: They construct a dataset covering 13 PLs with nearly 14K instances to study cross-lingual code knowledge transfer in RACG.
Outcome: The proposed model shows unequal cross-lingual knowledge transfer even with direct injection and shows limited reliance on natural language information embedded in code when equipped with a code-specific retriever.
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation (2025.findings-acl)

Copied to clipboard

Challenge: Large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation.
Approach: They propose a framework that allows large language models to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.
Outcome: The proposed framework enables LLMs to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods often apply coarse-grained constraints over entire reasoning trajectories . Existing approaches often apply unsafe constraints, causing unsafe outputs .
Approach: They propose a trajectory-level training framework that mitigates Self-Jailbreak . they propose 'chain-of-guardrail' to mitigate self-jailbreak by targeting step-level interventions .
Outcome: The proposed framework mitigates Self-Jailbreak by targeting step-level interventions while maintaining reasoning ability.
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have identified significant redundancy in large language models . quantization and pruning are two methods that reduce computational resources .
Approach: They propose simple pruning methods that prune redundant layers based on their BI scores.
Outcome: The proposed pruning methods demonstrate superior performance over previous pruning methods.
AutoAlign: Get Your LLM Aligned with Minimal Annotations (2025.acl-demo)

Copied to clipboard

Challenge: Automated Alignment (ALM) is a set of algorithms designed to align Large Language Models (LLMs) with human intentions and values while minimizing manual intervention.
Approach: They propose an open-source toolkit that integrates mainstream automated algorithms through a consistent interface and an accessible workflow supporting one-click execution for prompt synthesis and automatic alignment signal construction.
Outcome: The proposed framework enables easy reproduction of existing results through extensive benchmarks and facilitates the development of novel approaches via modular components.
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating presentations from documents focus on improving and evaluating content quality in isolation, overlooking visual appeal and structural coherence.
Approach: They propose an edit-based presentation generation system that analyzes and iterates on slides to create new slides.
Outcome: The proposed presentation generation tool outperforms existing methods in three dimensions . it analyzes slides, iterates and generates edit actions based on selected slides .
Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference (2026.findings-acl)

Copied to clipboard

Challenge: Existing cache eviction strategies for autoregressive language models fail to account for the role of mask tokens and specific characteristics in dLLMs.
Approach: They propose a training-free cache eviction framework tailored to dLLMs that denies a fully masked sequence and allows parallel decoding at the expense of memory and computation.
Outcome: The proposed framework reduces the cost of memory and cache eviction and improves efficiency by reducing allocation in intermediate layers and concentrating resources on prompt-preferring heads.
Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025.acl-long)

Copied to clipboard

Challenge: Existing Chinese resources are small in scale and limited to specific domains, making them insufficient for LLM post-training.
Approach: They propose a Chinese-annotated reward model and a preference dataset to address this gap . they evaluate Chinese RMs on CheemsBench and construct an RM that captures human preferences .
Outcome: The proposed RM achieves state-of-the-art performance on CheemsBench and CheeMePreference.
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)

Copied to clipboard

Challenge: Recent studies in formal mathematical reasoning have shown an unstoppable growth trend.
Approach: They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs.
Outcome: The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps.

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