List your company

Single-hop Question Answering on NarrativeQA

23.89ScoreDCS
-0.7597685.63969112.0391518.438609Jun 1, 2025

Evaluation results

MethodLinks
DCSBackbone=Llama-3-8B-Instruct2025.0623.89—
Llama-3-8B-InstructBackbone=Llama-3-8B-Instruct, Context Management=Baseline2025.0621.54—
Mistral-7B-InstructBackbone=Mistral-7B-Instruct, Context Management=Baseline2025.0620.89—
InfLLMBackbone=Llama-3-8B-Instruct2025.0619.62—
StreamingBackbone=Llama-3-8B-Instruct2025.0619.3—
LM-infiniteBackbone=Llama-3-8B-Instruct2025.0618.83—
DCSBackbone=Mistral-7B-Instruct2025.0618.63—
MOICEBackbone=Mistral-7B-Instruct2025.0617.03—
InfLLMBackbone=Vicuna-7B2025.0616.07—
DCSBackbone=Vicuna-7B2025.0615.6—
StreamingBackbone=Vicuna-7B2025.0615.37—
Vicuna-7BBackbone=Vicuna-7B, Context Management=Baseline2025.0614.95—
MOICEBackbone=Vicuna-7B2025.0614.84—
InfLLMBackbone=Mistral-7B-Instruct2025.0614.59—
LM-InfiniteBackbone=Vicuna-7B2025.0614.12—
LM-infiniteBackbone=Mistral-7B-Instruct2025.0612.87—
StreamingBackbone=Mistral-7B-Instruct2025.0612.6—
Llama-3-8B-Instruct with DCSBackbone=Llama-3-8B-Instruct, Context Strategy=DCS2025.060.23890.355
Llama-3-8B-InstructBackbone=Llama-3-8B-Instruct, Context Strategy=None2025.060.21540.276
Llama-3-8B-Instruct with InfilmBackbone=Llama-3-8B-Instruct, Context Strategy=Infilm2025.060.19620.2715
Llama-3-8B-Instruct with StreamingBackbone=Llama-3-8B-Instruct, Context Strategy=Streaming2025.060.1930.2426
Llama-3-8B-Instruct with LM-infiniteBackbone=Llama-3-8B-Instruct, Context Strategy=LM-infinite2025.060.18830.242