--- title: "Lei Li — papers, page 2 — Elamur Research" description: "Lei Li, Jiangsu University: 35 papers on Elamur Research (2019–2026), h-index 46 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/lei-li/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/lei-li/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/) / page 2 # Lei Li · page 2 35 papers in our library · 2019–2026 · page 2 of 2 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/lei-li/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/lei-li/) [1](https://md.research.elamur.ai/free/en/authors/lei-li/) **2** 26. **[ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers](https://md.research.elamur.ai/free/en/papers/zhang-2023-algo-synthesizing-algorithmic-programs-llm/)** *(2023 · 19 citations)* LLMs handle code generation well when a task spells out exactly what to implement. They do much worse on competitive-programming problems, where the model must first choose an efficient algorithm, and their output still needs human checking. ALGO tackles both issues. It builds on an observation: writing a slow… 27. **[The Role of Deductive and Inductive Reasoning in Large Language Models](https://md.research.elamur.ai/free/en/papers/cai-2025-role-deductive-inductive-reasoning-large/)** *(2025 · 17 citations)* Prompting methods such as Tree of Thought improve LLM reasoning by exploring many output paths, but this is expensive, and fixed prompt templates adapt poorly to harder instances. 28. **[Could Thinking Multilingually Empower LLM Reasoning?](https://md.research.elamur.ai/free/en/papers/gao-2025-could-thinking-multilingually-empower-llm/)** *(2025 · 10 citations)* LLMs are usually assumed to reason best in English. Recent evidence shows that some non-English languages can outperform English on reasoning benchmarks. This paper asks how much accuracy could be gained by having a model reason over the same question in many languages and pooling the results. 29. **[Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation](https://md.research.elamur.ai/free/en/papers/liu-2026-mending-holes-mitigating-reward-hacking/)** *(2026 · 2 citations)* LLM translation quality drops sharply for low-resource languages, and the usual post-training fixes require parallel or preference data that these languages often lack. 30. **[CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback](https://md.research.elamur.ai/free/en/papers/sun-2026-codeevo-interaction-driven-synthesis-code/)** *(2026 · 1 citation)* Training code-generation LLMs requires large numbers of instruction–code pairs. Manual curation is expensive, and popular automatic methods such as Self-Instruct and Evol-Instruct depend on fixed prompting heuristics. As a result, they often produce vague tasks and code that fails to compile or pass its tests.… 31. **[How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation](https://md.research.elamur.ai/free/en/papers/yang-2026-how-chain-thought-works-tracing/)** *(2026 · 1 citation)* Chain-of-Thought (CoT) prompting reliably improves LLM reasoning, but earlier explanations of why it works were mostly intuitive and not tied to model internals. 32. **[A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation](https://md.research.elamur.ai/free/en/papers/xue-2026-practical-evaluation-method-long-form/)** *(2026)* The paper addresses the lack of a reproducible way to evaluate simultaneous speech-to-speech translation (SimulS2ST) on long, unsegmented speech. 33. **[DIMAS-OMOP: A Deliberative Intelligence-Based Multi-Agent System for Chinese Medical Text Standardization toward OMOP](https://md.research.elamur.ai/free/en/papers/lv-2026-dimas-omop-deliberative-intelligence-based/)** *(2026)* Converting free-text Chinese radiology/imaging reports into the OMOP CDM v5.4 is difficult. Rule-based tools break on abbreviations and phrasing variants, BERT-style extractors need costly expert annotation, and LLMs give inconsistent outputs or require cloud APIs that conflict with patient-privacy rules. The authors… 34. **[Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech](https://md.research.elamur.ai/free/en/papers/ouyang-2026-hierarchical-policy-optimization-simultaneous-translation/)** *(2026)* Simultaneous speech translation (SST) systems built on LLMs can handle unbounded, hours-long audio efficiently when framed as a multi-turn dialogue that reuses the KV cache. 35. **[When “Correct” Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?](https://md.research.elamur.ai/free/en/papers/peng-2026-when-correct-is-not-safe/)** *(2026)* Code agents are usually judged by whether their patches resolve an issue and pass the test suite. This paper argues that passing tests does not mean a patch is secure. The authors define a threat class called functionally correct yet vulnerable (FCV) patches: fixes that pass every test but still contain a… [← prev](https://md.research.elamur.ai/free/en/authors/lei-li/) [1](https://md.research.elamur.ai/free/en/authors/lei-li/) **2**