Papers by Haoyu Tang

8 papers
Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data.
Approach: They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.
Outcome: The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark.
Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to reduce memory footprint of long-context LLMs rely on RoPE-induced oscillations.
Approach: They propose a frequency-domain framework that converts RoPE-induced oscillations into sparse spectral representations.
Outcome: The proposed framework achieves efficient compression with performance comparable to FP16 benchmarks.
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for textual and structural retrieval ignore mutual reinforcement and only use structural retrievals for text-rich Graph Knowledge Bases (TG-KBs).
Approach: They propose a Mixture of Structural-and-Textual Retrieval to retrieve textual and structural knowledge via a Planning-Reasoning-Organizing framework.
Outcome: Experiments show that the proposed framework performs better than existing methods in analyzing TG-KBs and integrating structural trajectories for candidate reranking.
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)

Copied to clipboard

Challenge: Retrieval-augmented Large Language Models struggle with complex inputs and noisy knowledge retrieval hindering model effectiveness.
Approach: They propose a query generation method that integrates query generation blending with knowledge filtering to enhance retrieval-augmented LLMs.
Outcome: The proposed approach surpasses state-of-the-art benchmarks on open-domain question answering benchmarks.
Empowering GraphRAG with Knowledge Filtering and Integration (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models suffer from knowledge gaps and hallucinations, resulting in incorrect or poor reasoning.
Approach: They propose Graph retrieval-augmented generation (GraphRAG) which integrates structured knowledge from external graphs to enhance model's reasoning.
Outcome: Experiments on knowledge graph QA tasks show that GraphRAG significantly improves reasoning performance across multiple backbone models.
PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models lack the capacity to formulate global strategies due to latency and availability constraints.
Approach: They propose a framework to internalize the strategic oversight of large models into intrinsic Latent Guidance by synthesizing a query-conditioned Latent Guide.
Outcome: The proposed framework outperforms strong baselines on mathematical and coding benchmarks with negligible inference latency.
Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in AI for biological research focus on integrating molecular data with natural language to accelerate drug discovery.
Approach: They propose a Language-based Automatic Annotation Augmentation framework that leverages large language models to augment existing datasets.
Outcome: The proposed framework outperforms state-of-the-art models on text-based tasks and validates its versatility and utility.
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach: They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome: Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.

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