Papers by Jie Bao

7 papers
IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to improve content visibility are static heuristic rules or optimize for heterogeneous queries.
Approach: They propose a "diverge-then-converge" framework that extracts optimization preferences from latent queries and synthesizes a global revision blueprint for guided editing.
Outcome: The proposed framework achieves substantial performance gains while maintaining robustness across diverse retrieval scenarios.
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach: They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome: The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.
Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives (2022.emnlp-main)

Copied to clipboard

Challenge: Recent research shows strong empirical advantages of dense retrieval in various information access scenarios, such as openQA.
Approach: They propose a method which accumulates momentum negatives from past iterations and approximates future iteration with lookahead negatives as "teleportations" on web search and OpenQA, ANCE-Tele outperforms previous state-of-the-art systems of similar size and eliminates the dependency on sparse retrieval negatives.
Outcome: The proposed method outperforms previous state-of-the-art systems on web search and OpenQA and is competitive among systems with significantly more parameters.
Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision (2021.acl-long)

Copied to clipboard

Challenge: Neural information retrieval models have shown advanced results in many ranking scenarios where massive relevance labels or clickthrough data are available.
Approach: They propose a domain adaptive learning method that generalizes Neu-IR models from label-rich source domains to few-shot target domains.
Outcome: The proposed method improves the few-shot ranking accuracy of Neu-IR models on three TREC benchmarks in the web, news, and biomedical domains.
Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing pipelines for generating high-quality, ultra-detailed image captions are limited by the scarcity of image caption data.
Approach: They propose a pipeline for generating high-quality, ultra-detailed image captions that integrates both pre-processing and post-processor stages.
Outcome: The proposed pipeline improves LVLMs' perception and cognitive abilities across multiple vision-language benchmarks.
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to generate human-aligned content with a “jailbreak prompt” are inefficient and repetitive, causing inefficiency and a lack of experience.
Approach: They propose a framework that integrates past attack experiences to aid current jailbreak attempts.
Outcome: The proposed framework improves both attack effectiveness and efficiency compared to the current black-box jailbreak method.
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)

Copied to clipboard

Challenge: Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence.
Approach: They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty.
Outcome: Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect.

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