Papers by Qian Cao

23 papers
MemoBrain: Executive Memory as an Agentic Brain for Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are inherently long-horizon, causing reasoning traces and tool artifacts to accumulate and strain the working context of large language models.
Approach: They propose a model that constructs a dependency-aware memory over reasoning steps and captures salient intermediate states and their logical relations.
Outcome: The proposed model prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget.
AWARE: Agentic Knowledge Warehousing for Contextual Intelligence (2026.findings-acl)

Copied to clipboard

Challenge: Large language models excel in information seeking tasks, but their knowledge is limited in coverage and timeliness.
Approach: They propose an agentic knowledge warehousing framework that transforms unstructured data into minimal, task-conditioned knowledge representations consumable by LLMs.
Outcome: Experiments on GAIA, WebWalker, and BrowseComp-Plus show improvements over baselines.
BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing work adopts separate modules for retrieval and generation, which may be suboptimal since the retrieval task and generation task cannot benefit from each other to improve performance.
Approach: They propose a backbone-shared RAG framework that uses a domain-specific corpus to continuously pre-train a model and then trains two plug-and-play Low-Rank Adaptation modules based on the shared backbone to minimize retrieval and generation losses respectively.
Outcome: The proposed framework outperforms baseline models by 5% and 13% in Hit@3 upon two datasets in retrieval evaluation and by 23% in terms of BLEU-3 in generation evaluation.
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction (2022.findings-acl)

Copied to clipboard

Challenge: Keyphrase extraction (KPE) extracts phrases in a document that provide a concise summary of the core content.
Approach: They propose an unsupervised keyphrase extraction method that ranks candidates by similarity between embeddings of source document and masked document.
Outcome: The proposed method outperforms state-of-the-art methods on six benchmarks . it achieves average 3.53 improvement over the existing method .
CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent Discovery (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to intent discovery cluster novel intents with prior knowledge from intent-labeled data in a semi-supervised way.
Approach: They propose a semi-supervised intent discovery framework CoCoID with two components . they propose to discriminate user utterance representation learning and intra-cluster knowledge distillation .
Outcome: The proposed framework outperforms state-of-the-art intent discovery models by over 1.4 ACC and ARI points and 1.1 NMI points across four datasets.
Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to compress long contexts have degraded dramatically as compression ratios increase, sometimes even falling to the closed-book level.
Approach: They propose a query-guided compression method that preserves key information within the compressed context.
Outcome: The proposed method can consistently perform well even at high compression ratios, and offers significant benefits in terms of inference cost and throughput.
DocAgent: A Multi-Agent System for Automated Code Documentation Generation (2025.acl-demo)

Copied to clipboard

Challenge: Existing methods for generating documentation using Large Language Models (LLMs) produce incomplete, unhelpful, or factually incorrect outputs.
Approach: They propose a novel collaborative system that uses topological code processing for incremental context building to generate documentation by agents.
Outcome: The proposed system outperforms baselines in completeness, helpfulness, and truthfulness evaluations.
Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Copied to clipboard

Challenge: Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach: They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome: The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.
INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent (2025.acl-long)

Copied to clipboard

Challenge: Recent advances have underscored the potential of large language model (LLM)-based agents in financial decision-making.
Approach: They propose to evaluate LLM agents using 13 different LLMs as backbone models across various market environments and tasks.
Outcome: The proposed framework assesses the reasoning and decision-making capabilities of 13 different LLMs across various market environments and tasks.
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling (2020.emnlp-main)

Copied to clipboard

Challenge: RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues spanning over 12 domains . despite of substantial progress made, there are challenges in creating challenging datasets in terms of size, multiple domains, semantic annotations and complexity.
Approach: They propose a large-scale multi-domain Chinese Wizard-of-Oz dataset with rich semantic annotations that captures discourse phenomena for task-oriented dialogue modeling.
Outcome: The proposed dataset contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues with more than 150K utterances spanning over 12 domains.
Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation (2026.findings-acl)

Copied to clipboard

Challenge: Autoregressive sequence modeling has been successful in many domains, but maintaining long-term coherence and structural integrity remains a challenge.
Approach: They propose an ACG paradigm that relies on anchor features from previously generated musical content to guide subsequent generation during the autoregressive process.
Outcome: The proposed framework outperforms existing methods in symbolic music generation tasks.
EoT: Evolution of Thoughts for Complex Reasoning Tasks (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing studies focus on ensuring behavior fidelity, factuality or reliability in generated reasoning processes, but they neglect the simultaneous optimization of all three aspects for each thought.
Approach: They propose a thought assessment method that is sensitive to knowledge and LLM behaviors . they use three scorers to evaluate each thought by considering domain context, semantic alignment, and behavior impact.
Outcome: The proposed framework outperforms advanced approaches in knowledge-based complex tasks.
Encoding Gated Translation Memory into Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Neural machine translation (MT) technology has made significant progress in the past few years.
Approach: They propose a method to combine the strengths of TM and neural machine translation (NMT) they use a gating mechanism to balance the impact of the TM match on the NMT decoder .
Outcome: The proposed method improves translation quality by over 10 BLEU points when fuzzy matches are higher than 50% on the UN corpus.
RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services (2026.acl-industry)

Copied to clipboard

Challenge: Social networking services (SNS) are critical infrastructure for global interaction . supervised fine-tuning (SFT) can improve in-domain performance, but it often induces a ”seesaw” trade-off with out-of-domain robustness .
Approach: They propose an SNS-oriented LLM with a progressive, RL-prioritized post-training paradigm for fast and stable adaptation.
Outcome: The proposed model improves over the previous 7B model by 2.41 on average . it also yields an 8.74 average gain over its Qwen3-4B base .
Reinforcing Agentic Search Via Reward Density Optimization (2026.acl-long)

Copied to clipboard

Challenge: Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic search, but its performance is often hindered by reward sparsity .
Approach: They propose a new research problem to improve the reward obtained per unit of exploration cost by using a system that decomposes long-horizon tasks into intermediate objectives and assigns process-level rewards to provide denser learning signals.
Outcome: The proposed framework outperforms strong baselines on several agentic search benchmarks and achieves comparable performance to that of advanced proprietary models.
ConvTrans: Transforming Web Search Sessions for Conversational Dense Retrieval (2022.emnlp-main)

Copied to clipboard

Challenge: Recent studies show that conversational dense retrieval is a promising technique for realizing conversational search, but its implementation is severely hindered by the lack of data.
Approach: They propose a method that transforms easily-accessible web search sessions into conversational search sessions to alleviate the data scarcity problem.
Outcome: The proposed method can transform easily-accessible web search sessions into conversational search sessions.
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Recent breakthrough models like OpenAI-o1 and DeepSeek-R1 show powerful task-solving capabilities, particularly advances in reasoning.
Approach: They propose future research directions that may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.
Outcome: The proposed research may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.
RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services (2025.emnlp-industry)

Copied to clipboard

Challenge: Social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement.
Approach: They propose a domain-specific LLM to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for social networking services.
Outcome: The proposed model achieves an average improvement of 14.02% across 8 major tasks and 7.56% in bilingual evaluation benchmark, compared with baseline models.
KaeDe: Progressive Generation of Logical Forms via Knowledge-Aware Question Decomposition for Improved KBQA (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for answering natural language questions are difficult to generate . lack of a logical form for complex graphs can negatively impact overall performance .
Approach: They propose a generate-then-retrieve method that converts questions into structured LF queries . they propose to combine knowledge-aware question decomposition and progressive LF generation .
Outcome: The proposed method achieves state-of-the-art (SOTA) performance on WebQuestionSP and ComplexWebQuestions benchmarks.
Search-Oriented Conversational Query Editing (2023.findings-acl)

Copied to clipboard

Challenge: Existing CQR models are not learned toward improving the downstream search performance . existing models generate the rewrite token-by-token from scratch .
Approach: They propose a text editing-based CQR model tailored for conversational search . they propose rewrite tokens are selected from the dialogue in a non-autoregressive fashion .
Outcome: The proposed model outperforms state-of-the-art models on three conversational search benchmarks while having low rewriting latency.
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity.
Approach: They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation.
Outcome: The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories.

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