Papers by Peng Di
BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to augment language models with external knowledge but they are limited by static nature of pre-training data. |
| Approach: | They propose a lightweight approach that compresses retrieved documents into highly dense textual summaries to integrate into in-context RAG. |
| Outcome: | The proposed approach reduces latency and costs while achieving high performance in open-domain questions. |
Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Haonan He, Yuchen Ren, Yining Tang, Ziyang Xu, Junxian Li, Minghao Yang, Di Zhang, Yuan Dong, Tao Chen, Shufei Zhang, Yuqiang Li, Nanqing Dong, Wanli Ouyang, Dongzhan Zhou, Peng Ye
| Challenge: | Biology-Instructions is the first large-scale instruction-tuning dataset for multi-omics biological sequences. |
| Approach: | They propose a large-scale instruction-tuning dataset for multi-omics biological sequences . they propose 'chatMultiOmics' to overcome limitations of current LLMs on multi-ome tasks . |
| Outcome: | The proposed dataset bridges LLMs and complex biological sequence-related tasks while maintaining conversational fluency. |
Grafting Pre-trained Models for Multimodal Headline Generation (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to generate video headlines with pre-trained language models are labor intensive and impractical. |
| Approach: | They propose to graft the encoder from the pre-trained video-language model on the generative pre-trainer model and propose a consensus fusion mechanism for the integration of different components. |
| Outcome: | The proposed model achieves strong results on a brand-new dataset collected from real-world applications. |
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)
Copied to clipboard
Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen
| Challenge: | Existing approaches to program repair are based on correctness alone. |
| Approach: | They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits. |
| Outcome: | The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing. |
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
Zekai Lin, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Lei Jiang, Yu Lu, Bob Simons, Shuang Liang, Minlong Peng
| Challenge: | Recent approaches to fine-tuning of large language models suffer from task interference and catastrophic forgetting. |
| Approach: | They propose a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance. |
| Outcome: | The proposed framework reduces interference and forgetting while releasing outdated parameters to recover plasticity. |
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026.acl-long)
Copied to clipboard
Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim
| Challenge: | Incomplete learning is widespread and heterogeneous in large language models . authors identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between SFT supervision and pre-training knowledge, internal inconsistencies within SFT data, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns. |
| Approach: | They propose a diagnostic-first framework that maps incomplete learning to causes . they identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between supervision and pre-training knowledge, internal inconsistencies, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns. |
| Outcome: | The proposed framework maps incomplete learning to causes using observable training and inference signals. |
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that Large Language Models can generate diverse solutions during the rollout phase. |
| Approach: | They propose a new approach that leverages Semantic Neighbor Mixing to generate diverse input representations by mixing anchor tokens and nearest semantic neighbors. |
| Outcome: | Experimental results show that the proposed approach improves on strong baselines and generalizes on out-of-distribution tasks. |
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models on diverse tasks with instructions. |
| Approach: | They propose a framework to identify informative tasks and then actively tune models on selected tasks. |
| Outcome: | The proposed method outperforms baseline strategies for task selection on NIV2 and Self-Instruct datasets. |
GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive Reasoning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for automated geometry problem solving lack labeled data. |
| Approach: | They propose a framework that integrates logic graph deduction and deep reinforcement learning to optimize geometry reasoning as a Markov Decision Process. |
| Outcome: | The proposed framework improves accuracy and interpretability in the Geometry3K dataset while maintaining correctness. |
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance (2025.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments demonstrate that our approach significantly alleviates task interference and forgetting. |
| Approach: | They propose a framework for supervised fine-tuning for large language models . they first fine-tail the model on each task to identify its core parameter regions . |
| Outcome: | The proposed framework outperforms vanilla fine-tuning and baselines on multiple public benchmarks on reasoning, dialogue, instruction following, and more. |
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026.findings-acl)
Copied to clipboard
Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim
| Challenge: | Existing approaches to generating reward models rely on voting-based mechanisms to evaluate CoT outputs. |
| Approach: | They propose an efficient generative reward modeling framework grounded in model-internal uncertainty. |
| Outcome: | The proposed framework reduces inference cost while improving answer accuracy. |
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging (D18-1)
Copied to clipboard
| Challenge: | Existing POS tagging methods for Twitter use labeled newswire text . however, Twitter users tend to mimic formal media expressions and develop linguistically informal styles. |
| Approach: | They propose to use newswire text to learn POS tagging for Twitter while twitter users are developing linguistically informal styles. |
| Outcome: | The proposed method achieves better performance than state-of-the-art methods on three different datasets. |
VKIE: The Application of Key Information Extraction on Video Text (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for extracting structured information from videos are coarse-grained at segment level and unable to capture finegrained information at the entity level. |
| Approach: | They propose a task for extracting hierarchical key information from visual texts on videos . they decouple the task into four subtasks and propose two implementation solutions . |
| Outcome: | The proposed solutions achieve remarkable performance and efficient inference speed on a well-defined dataset. |
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling (2025.emnlp-industry)
Copied to clipboard
Xiaoyu Liu, Di Liang, Hongyu Shan, Peiyang Liu, Yonghao Liu, Muling Wu, Yuntao Li, Xianjie Wu, Li Miao, Jiangrong Shen, Minlong Peng
| Challenge: | Generative RMs (GRMs) lack contextual and background information during inference, leading to incomplete evaluations. |
| Approach: | They propose a modular and interpretable framework that integrates side-branch models as auxiliary feature generators. |
| Outcome: | The proposed framework outperforms scalar and saline reward models in robustness and alignment with human preferences. |
BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Experiments show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models. |
| Approach: | They propose a universal, lightweight compressor that distills relevant evidence from retrieved documents into a concise summary for seamless integration into in-context RAG. |
| Outcome: | Experiments on four open-domain multi-hop question-answering datasets show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models. |
Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on dependency prior structure integration into pre-trained models is still unclear. |
| Approach: | They propose a dependency-based fusion attention paradigm which explicitly introduces dependency prior structure into pre-trained models and adaptively fuses it with semantic information. |
| Outcome: | The proposed model achieves state-of-the-art or competitive performance on 10 public datasets, demonstrating the benefits of adaptively fusing dependency structure in semantic matching task. |
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale (2026.acl-industry)
Copied to clipboard
| Challenge: | a 5minute downtime for an incident could result in a loss of 40 million dollars and erosion of user trust. |
| Approach: | They propose a multi-stage event unification engine that synergizes efficient indexing techniques with Large Language Models (LLMs) to make informed decisions on event merging. |
| Outcome: | The proposed system outperforms baseline methods in routing accuracy, clustering quality, and Signal-to-Noise Ratio. |
GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding (2025.acl-long)
Copied to clipboard
| Challenge: | Programming languages have rich semantics that are represented by graphs and not available from the surface form of source code. |
| Approach: | They propose to use graph neural networks and cross-modal alignment technologies to inject structural information of code into LLMs as an auxiliary task during finetuning. |
| Outcome: | The proposed framework improves on five code tasks with six different baseline LLMs, while incurring no cost at inference time. |
Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that RALMs generate baseless information or contradicts with the retrieved context. |
| Approach: | They propose a lightweight monitor that leverages fine-grained decoding dynamics to synchronously detect unfaithful sentences. |
| Outcome: | Empirical results show that SynCheck outperforms baseline faithfulness detection and FOD outperformed traditional strategies in terms of faithfulness. |