List your company

Single-hop Question Answering on Qasper

44.79ScoreLlama-3-8B-Instruct
16.08623.53830.9938.442Jun 1, 2025

Evaluation results

MethodLinks
Llama-3-8B-InstructBackbone=Llama-3-8B-Instruct, Context Strategy=None2025.0644.7927.6
Llama-3-8B-InstructBackbone=Llama-3-8B-Instruct, Context Management=Baseline2025.0644.79—
Llama-3-8B-Instruct with DCSBackbone=Llama-3-8B-Instruct, Context Strategy=DCS2025.0644.5935.5
DCSBackbone=Llama-3-8B-Instruct2025.0644.59—
Llama-3-8B-Instruct with InfilmBackbone=Llama-3-8B-Instruct, Context Strategy=Infilm2025.0644.3127.15
InfLLMBackbone=Llama-3-8B-Instruct2025.0644.31—
Llama-3-8B-Instruct with LM-infiniteBackbone=Llama-3-8B-Instruct, Context Strategy=LM-infinite2025.0642.5324.2
LM-infiniteBackbone=Llama-3-8B-Instruct2025.0642.53—
Llama-3-8B-Instruct with StreamingBackbone=Llama-3-8B-Instruct, Context Strategy=Streaming2025.0642.5224.26
StreamingBackbone=Llama-3-8B-Instruct2025.0642.52—
MOICEBackbone=Mistral-7B-Instruct2025.0630.89—
DCSBackbone=Mistral-7B-Instruct2025.0630.64—
Mistral-7B-InstructBackbone=Mistral-7B-Instruct, Context Management=Baseline2025.0630.19—
InfLLMBackbone=Vicuna-7B2025.0624.35—
DCSBackbone=Vicuna-7B2025.0623.81—
Vicuna-7BBackbone=Vicuna-7B, Context Management=Baseline2025.0623.38—
StreamingBackbone=Vicuna-7B2025.0623.38—
MOICEBackbone=Vicuna-7B2025.0623.3—
LM-InfiniteBackbone=Vicuna-7B2025.0622.94—
InfLLMBackbone=Mistral-7B-Instruct2025.0622.08—
LM-infiniteBackbone=Mistral-7B-Instruct2025.0617.3—
StreamingBackbone=Mistral-7B-Instruct2025.0617.19—