Papers by Yutao Xie
INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning (2024.acl-long)
Copied to clipboard
Yutao Zhu, Peitian Zhang, Chenghao Zhang, Yifei Chen, Binyu Xie, Zheng Liu, Ji-Rong Wen, Zhicheng Dou
| Challenge: | Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks, but their application to information retrieval tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language. |
| Approach: | They propose to use instruction tuning to enhance LLMs' proficiency in IR tasks by combining a dataset with manually written templates to analyze the effects of instruction design, template diversity, few-shot demonstrations, and the volume of instructions. |
| Outcome: | The proposed model can be used to perform query understanding, document understanding, and query-document relationship understanding tasks. |
Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) fine-tuned using rejection sampling retain only correct reasoning trajectories . however, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated errors, leaving a gap in how reasoning failures are modeled during training. |
| Approach: | They propose a fine-tuning strategy that reframes rejection sampling as a structured supervision construction process. |
| Outcome: | The proposed approach outperforms RFT on multiple math benchmarks while retaining only correct reasoning trajectories. |
FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) are prone to misuse and misinformation, posing serious compliance risks. |
| Approach: | They propose a bilingual red-teaming benchmark to test an LLM’s refusal of requests that violate financial compliance. |
| Outcome: | The proposed benchmark is based on real-world financial crime cases and ethical violations and includes 14 subcategories covering financial crimes and ethical breaches. |
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing story generation benchmarks focus mainly on plot quality and fluency, leaving consistency errors unexplored. |
| Approach: | They propose a benchmark to evaluate narrative consistency in long-form story generation. |
| Outcome: | Evaluating LLMs, we find consistency errors are common in factual and temporal dimensions . authors say the findings can inform future efforts to improve consistency in long-form narrative generation. |
CCEval: A Representative Evaluation Benchmark for the Chinese-centric Multilingual Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Multilingual machine translation (MMT) has gained more importance due to international business development and cross-cultural exchanges. |
| Approach: | They propose to use Chinese-centric MMT evaluation dataset to build an impartial and representative evaluation benchmark. |
| Outcome: | The proposed dataset covers more diverse linguistic features than other benchmarks and is highly representative and humancorrelated. |