Papers by Qichao Zhang

8 papers
CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic (2026.findings-acl)

Copied to clipboard

Challenge: Existing search agent pipelines rely on sparse outcome rewards, leading to inefficient exploration and unstable training.
Approach: They propose a tool-integrated reasoning framework that provides turn-level feedback via a retrospective critic mechanism.
Outcome: The proposed framework outperforms baselines in multi-hop reasoning benchmarks and achieves faster convergence and training stability.
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching (2026.acl-long)

Copied to clipboard

Challenge: Existing routing methods rely on direct mapping from queries to models based on surface-level features, leading to poor generalizability on out-of-distribution data.
Approach: They propose a new routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs.
Outcome: The proposed framework improves matching accuracy while lowering inference costs . it decouples linguistic surface forms from task-intrinsic requirements .
Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection (2026.acl-long)

Copied to clipboard

Challenge: Spec-o3 is a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection.
Approach: They propose a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection via interleaved multimodal chain-of-thought reasoning.
Outcome: Spec-o3 outperforms traditional visual inspection methods on rare-object inspection tasks.
Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to persuasive dialogue generation suffer from stance oscillation and low informativeness.
Approach: They propose reinforced instructional prompting, a method that ensures speaker characteristics consistently guide all stages of dialogue generation.
Outcome: The proposed method ensures speaker characteristics guide all stages of dialogue generation and aligns language use with speakers’ native languages to better capture cultural nuances.
Recent Advances in Speech Language Models: A Survey (2025.acl-long)

Copied to clipboard

Challenge: Text-based Large Language Models (LLMs) are a promising solution for end-to-end speech interaction.
Approach: They propose to build a framework that allows users to input text and translate it into speech . they propose to use a text-only LLM and a "textto-speech" framework to generate a response based on this transcription .
Outcome: The survey offers an overview of recent approaches to building SpeechLMs . it outlines core architectural components, training methodologies, evaluation strategies and challenges .
RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)

Copied to clipboard

Challenge: Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection.
Approach: They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples.
Outcome: The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples.
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Prior work limits search depth to reduce cost, but this often leads to underexploration of complex questions.
Approach: They propose a reinforcement learning framework that evaluates each search step via self-generated intermediate answers.
Outcome: Extensive experiments on multiple benchmarks show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality.
RLAE: Reinforcement Learning-Assisted Ensemble for LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Existing ensemble methods for ensembling large language models rely on fixed weighting strategies that fail to adapt to dynamic, context-dependent characteristics of LLMs.
Approach: They propose a framework that reformulates LLM ensemble through a Markov Decision Process.
Outcome: The proposed framework outperforms existing methods by 3.3% on a diverse set of tasks while achieving lower time latency.

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