Papers by Jiajun Cheng
The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025.acl-long)
Copied to clipboard
| Challenge: | despite near-perfect results, effectiveness of model editing in real-world applications remains unclear. |
| Approach: | They propose QAEdit and WILD to better reflect real-world use of model editing . they propose a benchmark aligned with widely used question answering datasets and a task-agnostic evaluation framework . |
| Outcome: | The proposed QAEdit benchmark and WILD evaluation framework show that current models perform worse than previously reported. |
MARCH: Multi-Agent Reinforced Check for Hallucination (2026.acl-long)
Copied to clipboard
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie Hu, Yu Qin, null Erchao.zec, Xiaoxi Jiang, null Guanjunjiang
| Challenge: | Existing methods to detect hallucinations suffer from inherent confirmation bias, where the verifier inadvertently reproduces the errors of the original generation. |
| Approach: | They propose a framework that enforces rigorous factual alignment by leveraging deliberate *information asymmetry* by combining a pipeline of three specialized agents: a Solver, a Proposer, and a Checker. |
| Outcome: | Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucinism rates. |
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)
Copied to clipboard
Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen
| Challenge: | Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected. |
| Approach: | They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans . |
| Outcome: | The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test . |
When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing dense retrieval methods have achieved notable progress, but their effectiveness in legal case retrieval remains limited. |
| Approach: | They propose a self-evolving framework for rule-driven query rewriting that enhances BM25 without any parameter training. |
| Outcome: | The proposed framework outperforms non-evolutionary baselines, including human-designed rules and greedy rule selection, especially when powered by a high-capacity core LLM. |
MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation (2026.acl-long)
Copied to clipboard
Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang, Jinxing Zhou, Changsen Yuan, Tian Lan, Ziqin Zhou, Yudong Li, Jiajun Xu, Jingyun Liao, YiMing Cheng, Xuefeng Chen, Xian-Ling Mao, Yousheng Feng
| Challenge: | Existing evaluation benchmarks for text-to-audio-video (T2AV) generation are largely designed for human-recorded videos or single-speaker settings. |
| Approach: | They propose a failure-driven diagnostic benchmark for multi-talker dialogue-centric audio-video generation. |
| Outcome: | The benchmark evaluates multi-speaker dialogue generation at four levels: audio-visual signal fidelity, temporal attribute consistency, social interaction, and cinematic expression. |
EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. |
| Approach: | They propose a synthetic data generation framework that leverages models’ established English-to-x (en2x) capabilities by extending English parallel corpora into omnidirectional datasets and developing an English-referenced quality evaluation proxy. |
| Outcome: | The proposed framework achieves significant improvement across 72 x2x directions while generalizing to enhance en2x performance. |
TRANS-ZERO: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have reshaped machine translation, but multilingual MT still relies heavily on parallel data for supervised fine-tuning. |
| Approach: | They propose a framework that leverages only monolingual data and the intrinsic multilingual knowledge of Large Language Models (LLMs). |
| Outcome: | The proposed framework matches models trained on large-scale parallel data and excels in non-English translation directions. |
MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown their strong ability in the field of machine translation, yet they suffer from high computational cost and latency. |
| Approach: | They propose a framework which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner. |
| Outcome: | The proposed framework transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner. |
DocHieNet: A Large and Diverse Dataset for Document Hierarchy Parsing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for document hierarchy parsing are limited due to the small scale and inconsistency of datasets. |
| Approach: | They propose a document hierarchy parsing dataset to compensate for the data scarcity problem and propose 'dHP' framework to grasp fine-grained text content and coarse-grounded pattern at layout element level. |
| Outcome: | The proposed framework grasps both fine-grained text content and coarse-grounded pattern at layout element level, enhancing the capacity of pre-trained text-layout models in handling multi-page and multi-level challenges. |
LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)
Copied to clipboard
Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li
| Challenge: | Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training. |
| Approach: | They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks. |
Improving Long-Context Translation via Self-Supervised Dual Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models with long context windows suffer from catastrophic information distortion, undermining the strict faithfulness required for translation. |
| Approach: | They propose a self-supervised post-training framework that improves long-document translation reliability via round-trip consistency. |
| Outcome: | The proposed framework improves long-document translation reliability via round-trip consistency. |