Papers by Jiaqi Wu

19 papers
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering (2025.acl-long)

Copied to clipboard

Challenge: Existing methods rely on entity vector matching, but the purpose of the question is abstract and difficult to match with specific entities. Existing approaches rely only on entity-vector matching, and there is a problem with multi-hop reasoning.
Approach: They propose a framework that constructs reasoning paths from purposes back to conditions using the KG ontology.
Outcome: Experiments on the WebQSP and CWQ datasets show that ORT significantly improves the capability of large language models in knowledge graph question answering tasks (KGQA).
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings (2025.findings-acl)

Copied to clipboard

Challenge: Visualized Document Retrieval (VDR) uses large vision-language models to encode document pages into embeddings.
Approach: They evaluate methods to reduce patch embeddings per page while minimizing performance degradation.
Outcome: The proposed method maintains 98.2% of retrieval performance with only 11.8% of original memory usage and preserves 94.6% effectiveness at 2% memory footprint.
Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing methods handle long-term memory (LTM) and short-term (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization.
Approach: They propose a framework that integrates LTM and STM management directly into the agent's policy and propose 'agentic memory' to train such unified behaviors.
Outcome: The proposed framework outperforms strong memory-augmented baselines on five long-horizon benchmarks and achieves higher-quality long-term memory and more efficient context usage.
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but are vulnerable to backdoor attacks.
Approach: They propose a chain-of-scrutiny approach which leverages LLMs’ unique reasoning abilities to mitigate backdoor attacks.
Outcome: The proposed model is well-suited for the popular API-only LLM deployments, enabling detection at minimal cost and with little data.
SlugNERDS: A Named Entity Recognition Tool for Open Domain Dialogue Systems (L18-1)

Copied to clipboard

Challenge: UCSC researchers have developed an open domain social bot aimed at casual conversation . NER and NEL are important preprocessing steps for understanding user intent in open domain dialogue systems.
Approach: They propose a tool for NER and NEL in open domain dialogue that addresses these challenges . they also propose two corpora based on 10,000 real user conversations .
Outcome: The proposed open domain social bot is aimed at casual conversation.
Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality (2023.eacl-main)

Copied to clipboard

Challenge: Experimental results show that our model outperforms strong baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.
Approach: They propose a topic-aware global-local centrality model to help select the salient context from all sub-topics.
Outcome: The proposed model outperforms baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach: They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome: The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.
SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention (2025.findings-emnlp)

Copied to clipboard

Challenge: Jailbreak attacks exploit vulnerabilities in large language models to induce undesirable behavior . existing defenses cannot dynamically adjust representations based on harmfulness of queries .
Approach: They propose a representation-aware representation method that shields LLMs from jailbreak attacks . SafeInt relocates jailbreak-related representations into the rejection region .
Outcome: The proposed method outperforms baseline defenses while maintaining utility . it relocates jailbreak-related representations into the rejection region .
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Copied to clipboard

Challenge: Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach: They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome: This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization.
Approach: They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach.
Outcome: The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks.
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to review scientific papers are limited by their content or quality . SEA is a framework for automated scientific review, but its contents are generic or partial.
Approach: They propose a framework for automated scientific review using large language models . they propose to use a standardized review dataset to fine-tune an LLM to generate high-quality reviews.
Outcome: The proposed framework can generate high-quality reviews from standardized datasets and improves on the existing feedback mechanisms.
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025.findings-acl)

Copied to clipboard

Challenge: Despite the promising performance of Large Vision Language Models, they sometimes generate incorrect outputs.
Approach: They propose a multi-modal reward model that aligns LVLMs with human preferences.
Outcome: The proposed model achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model.
SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model (2024.emnlp-demo)

Copied to clipboard

Challenge: Large language models (LLMs) have shown remarkable achievements across various language tasks.
Approach: They propose a scientific literature LLM and a knowledge service system based on it . they collect scientific literature and then pre-train it using autoregressive training .
Outcome: The proposed system provides literature investigation, paper reading, and academic writing functions.
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing strategies for spatial localization are limited due to their limited capacity to perceive positional data.
Approach: They propose a location-based approach that leverages locational data to optimize interaction preferences.
Outcome: The proposed approach achieves SOTA results across offline benchmarks and real-world evaluations.
PEAP: Proactive Embodied Action Sequence Planning with Joint Understanding of Vision and Audio Perception (2026.acl-long)

Copied to clipboard

Challenge: Embodied action sequence planning focuses on the capability of embodied agents to implement action planning via environmental perception without explicit human instructions.
Approach: They propose to use a multimodal dataset to evaluate the performance of multiple large language models to evaluate their models' environmental perception capabilities.
Outcome: The proposed model shows that it lacks accurate environmental perception capabilities and that it can improve on the PEAP dataset.
Chinese Court Simulation with LLM-Based Agents System (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies have neglected the systematic design and procedure evaluation of court simulations, which are critical to the credibility and usage of court simulators in practice.
Approach: They propose a court simulation paradigm based on the real-world procedure structure of Chinese courts and a framework that focuses on both legal judgment prediction and court procedure analysis.
Outcome: The proposed model outperforms judges and lawyers from the real trials in many aspects.
Implicit Discourse Relation Identification for Open-domain Dialogues (P19-1)

Copied to clipboard

Challenge: Discourse relation identification is a challenging problem in open-domain dialogue systems . previous work relies on formal text but this data is not suitable for informal dialogue .
Approach: They propose a method to automatically extract the implicit discourse relation argument pairs from dialogic turns and a pipeline to identify them.
Outcome: The proposed pipeline extracts argument pairs from dialogic turns and improves it by performing feature ablation and incorporating dialogue features.
StyleDGPT: Stylized Response Generation with Pre-trained Language Models (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for generating responses following a desired style are lacking of parallel data for training.
Approach: They propose a KL loss and a style classifier to fine-tune response generation . they show that their model can significantly outperform state-of-the-art methods .
Outcome: The proposed model outperforms state-of-the-art models in style consistency and contextual coherence with two public datasets.

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