Papers
Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: What is the effect of instruction fine-tuning on language model mathematical problem-solving accuracy v9. 15 claims were extracted from source literature; 1 was independently verified against retrieved documents.…
Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does pretraining data quality affect language model reasoning benchmark performance v9. 12 claims were extracted from source literature; 1 was independently verified against retrieved documents. An automated…
Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How do multimodal language models perform on visual mathematical and scientific reasoning v9. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does reinforcement learning from human feedback improve language model mathematical reasoning v9. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 1 peer-reviewed paper addressing the following research question: What architectural innovations improve transformer performance on multi-step logical reasoning v9. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How do sparse mixture-of-experts models compare to dense transformers on mathematical reasoning v9. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: What is the relationship between model scale and emergent reasoning capabilities in transformers v9. 16 claims were extracted from source literature; 3 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 16 peer-reviewed papers addressing the following research question: How does test-time compute scaling improve language model performance on reasoning benchmarks v9. 11 claims were extracted from source literature; 0 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: What is the accuracy gap between Qwen-Max-VL and proprietary models on the LogicVista puzzle-solving subset. 0 claims were extracted from source literature; 0 were independently verified against retrieved…
Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How do adversarial perturbations or input variations affect the robustness of DeepSeek-33B's solutions in the self-invoking code generation setting, compared to baseline models. 0 claims were extracted from…
Abstract: This report synthesises findings from 16 peer-reviewed papers addressing the following research question: What is the performance degradation of LLaMA-8B on MATH benchmark when subjected to adversarial perturbations in problem statements. 13 claims were extracted from source literature; 2 were independently verified…
Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: What is the impact of quantization techniques (e.g., 4-bit vs 8-bit) on DeepSeek-1.3B's inference throughput and accuracy in solving GSM8K-V math word problems. 0 claims were extracted from source literature; 0…
Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How robust is LLaVA-OneVision-72B to domain shifts when evaluated on out-of-distribution visual mathematics problems compared to text-only reasoning benchmarks like GSM8K. 0 claims were extracted from source…
Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the performance of llava-v1.6-mistral-7b compare to other state-of-the-art multimodal models on HumanEval-V for diagram interpretation tasks, particularly in accuracy and reasoning depth. 11 claims were…
Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How does InstructionBlip-7b perform on adversarial NLU tasks compared to standard GLUE benchmarks. 12 claims were extracted from source literature; 5 were independently verified against retrieved documents. An…
Abstract: This report synthesises findings from 4 peer-reviewed papers addressing the following research question: To what extent can fine-tuning llava-v1.6-mistral-7b on domain-specific diagram datasets improve its performance on HumanEval-V coding tasks. 17 claims were extracted from source literature; 3 were independently…
Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How does the performance of LLaVA-OneVision-72B on visual mathematical reasoning tasks compare to other state-of-the-art multimodal models like Qwen-VL or DeepSeek-VL on the GSM8K-V benchmark. 0 claims were…
Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of LLaDA-8B on reasoning mathematics coding and language understanding tasks. 14 claims were extracted from source literature; 2 were independently verified against…
Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of GPT-4V on reasoning mathematics coding and language understanding tasks. 0 claims were extracted from source literature; 0 were independently verified against…
Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of LLaMA-1B on reasoning mathematics coding and language understanding tasks. 14 claims were extracted from source literature; 1 was independently verified against…
Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of Claude-3-7-Sonnet on reasoning mathematics coding and language understanding tasks. 14 claims were extracted from source literature; 1 was independently verified…
Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of Vicuna-13B on reasoning mathematics coding and language understanding tasks. 14 claims were extracted from source literature; 2 were independently verified against…
Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of Qwen-Max-VL on reasoning mathematics coding and language understanding tasks. 0 claims were extracted from source literature; 0 were independently verified against…
Abstract: This report synthesises findings from 16 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of LLaMA-8B on reasoning mathematics coding and language understanding tasks. 0 claims were extracted from source literature; 0 were independently verified against…
Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: What are the benchmark performance scores of LLaMA-3B on reasoning mathematics coding and language understanding tasks. 0 claims were extracted from source literature; 0 were independently verified against…