Papers by Jianfeng Cai
Interactive Text Generation (2023.emnlp-main)
Copied to clipboard
Felix Faltings, Michel Galley, Kianté Brantley, Baolin Peng, Weixin Cai, Yizhe Zhang, Jianfeng Gao, Bill Dolan
| Challenge: | Advances in generative modeling have made it possible to automatically generate high-quality texts, code, and images, but they can be unsatisfactory in many respects. |
| Approach: | They propose a task that allows training generation models interactively without the costs of involving real users. |
| Outcome: | The proposed model trains with Imitation Learning without the cost of involving real users and is superior to non-interactive models. |
Active Generalized Category Discovery with Diverse LLM Feedback (2026.eacl-long)
Copied to clipboard
| Challenge: | Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabeled data using limited labeled data from known categories. |
| Approach: | They propose a framework for generalized category discovery that actively learns from diverse and collaborative feedback. |
| Outcome: | The proposed framework improves instance-level contrastive features, generates category descriptions, and aligns uncertain instances with LLM-selected category descriptions. |
CodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case Generation (2026.findings-acl)
Copied to clipboard
Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Kangwen Zhao, Dongyun Xue, Mingxiao Feng, Wengang Zhou, Houqiang Li
| Challenge: | Existing approaches to synthesize test cases using Large Language Models (LLMs) rely on the model’s intrinsic generation capabilities without external feedback, resulting in insufficiently diverse cases. |
| Approach: | They propose a feedback-driven iterative framework that leverages Large Language Models to generate initial test cases, execute them against known correct and incorrect solutions, and utilizes the failed results as feedback to guide the LLM in refining the test cases toward high fidelity and discriminability. |
| Outcome: | The proposed method outperforms the existing codecontests and codecontests+ models by 4.30% and 8.78%. |
SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants? (2025.emnlp-main)
Copied to clipboard
Yao Dou, Michel Galley, Baolin Peng, Chris Kedzie, Weixin Cai, Alan Ritter, Chris Quirk, Wei Xu, Jianfeng Gao
| Challenge: | Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn conversations. |
| Approach: | They propose to use large language models to simulate users for automatic assistant evaluation. |
| Outcome: | The proposed model outperforms human evaluations on two interactive tasks and achieves Spearman’s of 0.7 on both tasks. |
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection (2024.naacl-long)
Copied to clipboard
| Challenge: | Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data. |
| Approach: | They propose a scoring approach that encapsulates three primary dimensions of summarization model quality. |
| Outcome: | The proposed method reduces reliance on human-labeled data and improves the performance of summarization models. |
Bias Fitting to Mitigate Length Bias of Reward Model in RLHF (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to tackling length bias are limited by their complexity or lack of a linear length-reward relation. |
| Approach: | They propose a framework that learns and corrects underlying bias patterns by fitting a length-reward relationship into a reward model. |
| Outcome: | The proposed framework improves length-controlled win rate and reduces verbosity without compromising performance. |
Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training (2024.eacl-long)
Copied to clipboard
| Challenge: | End-to-end (E2E) spoken language understanding models are constrained by the cost of collecting speech-semantics pairs. |
| Approach: | They propose a model that learns E2E SLU without speech-semantics pairs . they propose cross-modal selective self-training (CMSST) to address imbalance and noise issues . |
| Outcome: | The proposed model learns E2E SLU without speech-semantics pairs . the proposed model requires the domains of speech-text and text-sensitization to match . |