Papers by Jianhua Tao
Two-Stage Regularization-Based Structured Pruning for LLMs (2026.acl-long)
Copied to clipboard
Mingkuan Feng, Jinyang Wu, Siyuan Liu, Shuai Zhang, Hongjian Fang, Ruihan Jin, Feihu Che, Pengpeng Shao, Zhengqi Wen, Jianhua Tao
| Challenge: | Structural pruning is a promising solution for large language models . prior structured pruning methods remove unimportant parameters based on certain metrics . |
| Approach: | They propose a structural pruning method that iteratively learns the weights of transformer layers by adding their l1-norm to the loss function. |
| Outcome: | The proposed pruning method outperforms strong layer-wise pruning methods without requiring retraining. |
ReFL: Reflective Feedback Learning for Hallucination Detection of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for detecting hallucinations depend on external knowledge sources, incurring high computational costs and limiting real-time applicability, or extract the model’s internal states, leading to poor generalization. |
| Approach: | They propose a hallucination detection framework that leverages corrective in-context learning to guide LLMs to recognize their own prediction errors and adjust internal representations, critically without updating model weights. |
| Outcome: | The proposed framework outperforms existing methods on two benchmark datasets and achieves state-of-the-art performance. |
Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to assess human emotion are limited by the subjective nature of emotion perception, limiting the robustness of existing models. |
| Approach: | They propose a plug-and-play module that enhances MLLMs’ ability to tackle compound and context-rich emotion tasks. |
| Outcome: | The proposed framework improves MLLMs' ability to tackle compound and context-rich emotion tasks and the Compound Emotion QA dataset shows it performs well across both benchmarks and evaluation frameworks. |
SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for training large language models waste computation budget on trivial steps while failing to guarantee sample quality. |
| Approach: | They propose a framework that selectively branches at critical decision states for resource-efficient exploration. |
| Outcome: | The proposed framework activates adaptive branching exploration at critical decision states to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage. |
RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current routing methods are limited in exploring the connection between query and LLM characteristics. |
| Approach: | They propose a framework for LLM routing that uses a transformer-based backbone and a radial structure to articulate the query-LLMs relationship. |
| Outcome: | The proposed framework outperforms existing routing methods by 9.2% and 5.8% on RouterBench. |
TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning (2026.findings-acl)
Copied to clipboard
Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, Jianhua Tao
| Challenge: | Existing RL methods rely on unstructured self-sampling to fit scalar rewards, resulting in inefficient rollouts. |
| Approach: | They propose a structured template-guided RL framework that augments policy optimization with explicit template guidance. |
| Outcome: | Experiments show that TemplateRL outperforms GRPO and GRPI by 99% on AIME and 41% on AMC with superior stability on weak models and remarkable cross-domain generalization. |
Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models (2026.acl-long)
Copied to clipboard
Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian, Jianhua Tao
| Challenge: | In-context learning (ICL) struggles with complex reasoning due to superficial, example-level implicit imitation. |
| Approach: | They propose an automated method that shifts from surface-level examples to more guidance-oriented thought patterns. |
| Outcome: | The proposed method achieves 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5% accuracy. |
Pandora’s Box or Aladdin’s Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address hallucinations in large language models (LLMs). |
| Approach: | They define seven distinct noise types from a linguistic perspective and establish a Noise RAG Benchmark (NoiserBench) they propose to evaluate noise that is beneficial to LLMs and noise that's harmful to LRMs. |
| Outcome: | The proposed framework consists of seven distinct noise types from a linguistic perspective and includes multiple datasets and reasoning tasks. |
Bilateral Masking with prompt for Knowledge Graph Completion (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing word matching methods fail to obtain satisfactory single embedding representations for entities. |
| Approach: | They propose a bi-encoder-based approach to enhance entity representations by using prompts to narrow the distance between the predicted entity and the known entity. |
| Outcome: | The proposed model achieves state-of-the-art performance on the WN18RR dataset. |
ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning (2026.findings-acl)
Copied to clipboard
Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao
| Challenge: | Existing approaches to optimize large language models with external tools are limited. |
| Approach: | They propose a dual-path framework for dynamic tool usage in cross-domain complex reasoning . they exploit empirical priors for domain-specific alignment and RL-based multi-step routing . |
| Outcome: | The proposed framework outperforms closed-source models and existing methods on in-distribution and out-of-distortion tasks. |
NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption (2024.lrec-main)
Copied to clipboard
| Challenge: | Pre-trained Language Models (PLMs) have superior performance on downstream tasks . however, conventional TAPT adjusts all parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLM's weights. |
| Approach: | They propose a two-step n-gram enhanced low-rank task adaptive pre-training method to customize a PLM to the downstream task. |
| Outcome: | The proposed method improves performance on six datasets from four domains. |
CAIR: Causal Adaptive Information-based Reinforcement Learning for Multimodal Emotion Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multimodal emotion reasoning produce fluent but superficial explanations that lack authentic logical derivation. |
| Approach: | They propose a framework that treats rationales as causal mediators between raw perceptual signals and emotional semantics and an adaptive optimization mechanism to balance perception and reasoning across varying cognitive loads. |
| Outcome: | The proposed framework outperforms specialized SFT models by 14.4% while enhancing rationale faithfulness. |
CoDA: Restoring Contextual Dominance via Copy-Encouraged Attention Intervention for Mitigating RAG Hallucinations (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation reduces hallucination by grounding outputs in external evidence. |
| Approach: | They propose a lightweight inference-time attention intervention that amplifies evidence-aligned value states to enhance contextual faithfulness and reduce hallucination. |
| Outcome: | The proposed model reduces hallucination by grounding model outputs in external evidence. |