Pengfei Liu · page 2
Papers
- Halu-J: Critique-Based Hallucination Judge (2024 · 8 citations)
LLMs often produce factually wrong statements. Retrieval-based detectors usually reduce the check to a bare label. They give little justification, can be thrown off by off-topic retrieved passages, and weigh all evidence equally. Halu-J addresses this with an open judge model of 7 billion parameters. Given a claim… - DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models (2026 · 7 citations)
Popular medical LLM benchmarks such as MedQA and MMLU are nearly saturated, with leading models scoring above 90%. - SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026 · 1 citation)
Modern LLMs advertise very long context windows, yet they handle long sequences of numbers poorly. Tasks such as counting, filtering, or spotting trends need exact access to every value. The authors trace this failure to attention dispersion: as inputs grow, Softmax spreads attention over many similar numeric tokens… - Test-Time Adaptation of an Offline Multimodal Foundation Model for Simultaneous Speech Translation (2026 · 1 citation)
The paper addresses end-to-end simultaneous speech-to-text translation (SimulST), where systems usually need complex architectures and dedicated training. - SciPedia: Unlocking the Value of Scientific Data for Pre-training (2026)
Academic books and research papers are among the richest sources of high-quality text. Open LLM pre-training seldom uses them because public scientific corpora are mostly web-filtered or narrow, and much of the literature is locked inside PDFs. The authors collect books and papers from original sources and process…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/pengfei-liu/page/2/