Qi Liu

Evaluation & Benchmarks · with Cao · 2023

A researcher in the Science corpus: 1 paper; trusts 2 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Evaluation & Benchmarks — 9 citations into it
• Natural Language Processing — 8 citations into it

Whom Qi Liu trusts

Their strongest outbound trust, strongest first, inferred from their citations.

1. Chin-Yew Lin (in Evaluation & Benchmarks)
2. M. McHugh (in Evaluation & Benchmarks)

Papers from Qi Liu's perspective

Ordered by how strongly the researchers Qi Liu trusts endorse each paper. Same corpus, a different order for every researcher.

1. Bleu: a Method for Automatic Evaluation of Machine Translation
2. ROUGE: A Package for Automatic Evaluation of Summaries
3. BERTScore: Evaluating Text Generation with BERT
4. GPT-4 Technical Report
5. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena
6. Instruction Tuning with GPT-4
7. Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
8. BARTScore: Evaluating Generated Text as Text Generation
9. LIMA: Less Is More for Alignment
10. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

Their papers

• Large Language Models are not Fair Evaluators (2023) — 1,116 citations