LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K — mentioned by zone411

Mon, 01 Apr 2024 04:00:56 GMT

We really need better long context benchmarks than needle-in-a-haystack. There is LV-Eval (https://arxiv.org/abs/2402.05136) with multi-hop QA that's better but still pretty basic.

Paper and discussion history. A mention is not an endorsement.

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K · HackerPapers discussions

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K — mentioned by zone411