text string | source string |
|---|---|
education using large language models,” PLOS Digital Health , vol. 2, no. 2, p. e0000198, Feb. 2023. [Online]. Available: https://dx.plos.org/10.1371/journal.pdig.0000198 [7] A. Gilson, C. W. Safranek, T. Huang, V . Socrates, L. Chi, R. A. Taylor, and D. Chartash, “How Does ChatGPT Perform on the United States Medical ... | https://arxiv.org/abs/2505.16648v1 |
Learning for Medical Question Answering,” Dec. 2023. [Online]. Available: http://medrxiv.org/lookup/doi/10.1101/2023.12.21.23300380 [19] J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. Chi, Q. Le, and D. Zhou, “Chain-of-thought prompting elicits reasoning in large language models,” 2023. [Online]. Avail... | https://arxiv.org/abs/2505.16648v1 |
Can reasoning models comprehend mathematical problems in Chinese ancient texts? An empirical study based on data from Suanjing Shishu Chang Liu1, Dongbo Wan g1, Liu liu1, Zhixiao Zhao1 1 (College of Information Management, Nanjing Agricultural University, Nanjing, China ) Abstract : This study addresses the challenges ... | https://arxiv.org/abs/2505.16660v1 |
of mathematical problems from Suanjing Shishu ( 《算经十书 》), the most renowned collection of Chinese mathematical works, to construct a reasoning model evaluation benchmark. We systematically evaluate and analyze the performance of mainstream reasoning models on ancient mathematical tasks. Through empirical investigation,... | https://arxiv.org/abs/2505.16660v1 |
SFT (Supervised Fine -tuning) models using reinforcement learning algorithms with preference data to improve response safety, usefulness, and robustness This three -stage optimization framework significantly enhanced LLMs' question -answering performance. Numerous institutions subsequently adopted this approach to deve... | https://arxiv.org/abs/2505.16660v1 |
accura cy. Existing benchmarks for evaluating unimodal large language models and reasoning models predominantly focus on mathematical word problems, where problems are described in natural language rather than symbolic notation, requiring models to comprehend the problem's context and provide solutions. Notable example... | https://arxiv.org/abs/2505.16660v1 |
based on extensiv e research, introducing a series of ancient Chinese scientific and technological achievements —including mathematics —to the West. This work overturned prevailing misconceptions about China's mathematical heritage. In V olume 3 of the series, Dr. Needham cata loged mathematical literature and accompli... | https://arxiv.org/abs/2505.16660v1 |
1963) and G uo Shuchun (Guo, S. C. & Liu, D., 1998) systematically annotated variants in different editions of the Suanjing Shishu , revealing the original forms of high -quality ancient texts to the public. In the era of rapid information technology and AI development, researchers have explored digitization and intell... | https://arxiv.org/abs/2505.16660v1 |
from the official website of the Chinese Philosophy E -Book Project (Sturgeon, n.d.). On this platform, The Nine Chapters on the Mathematical Art , Sunzi suanjing , The Sea Island Mathematical Classic , and Zhou Bi Suan Jing had already undergone manual collation and punctuation annotation, making their texts directly ... | https://arxiv.org/abs/2505.16660v1 |
iron into steel, each jin (Chinese pound) reduces by three liang (Chinese ounces). Yet, the fifth problem’s description omits this premise, merely referencing “according to the previously mentioned consumption rate.” If such problems with default conditions are automatically extracted without contextual an alysis, crit... | https://arxiv.org/abs/2505.16660v1 |
techniques and methods in ancient Chinese texts and provided examples corresponding to each category. This study referenced Needham’s classification framework, categorizing the mathematical methods reflected in Suanshu Shijin into 15 types. Using a rea soning model, we instructed it to output all mathematical methods i... | https://arxiv.org/abs/2505.16660v1 |
for Levels 1 –4, respectively. Table 3 shows the distribution of problems across the eight classics: Table 3 Distribution of Problems by Difficulty Level in Ancient Texts Classic Name Level 1 Level 2 Level 3 Level 4 The Nine Chapters on the Mathematical Art 6 92 88 13 The Sea Island Mathematical Classic 0 0 3 6 Zhang Q... | https://arxiv.org/abs/2505.16660v1 |
a model’s abil ity to interpret and solve classical mathematical problems. 2.2.2 Model Selection The open -sourcing of DeepSeek R1 has advanced the democratization of large -scale reasoning models. Recent research has demonstrated that strong long -context reasoning capabilities can be replicated even in mid -sized lan... | https://arxiv.org/abs/2505.16660v1 |
judgment results were used for the final accuracy calculation, thereby quantifying the performance of the reasoning model in solving ancient mathematical problem s. 3 Experimental Results 3.1 Experimental Environment and Hyperparameter Design The model was executed on a Linux server equipped with two A800 GPUs. The sys... | https://arxiv.org/abs/2505.16660v1 |
caused overfitting. Across all models, performance peaked at Level 1 (simple arithmetic), with accuracy declining as difficulty increased, indicating struggles with complex classical problems. Furthermore, all models underperformed compared to their English Math -500 benchmark results (≥70%), despite Math -500 covering... | https://arxiv.org/abs/2505.16660v1 |
Plus and QwQ -32B demonstrate notable overall performance gains. Qwen -Plus achieves optimal performance, solving 5 more medium -difficulty math problems correctly than Deepseek R1. Meanwhile, QwQ -32B nearly perfectly answers all simple questions, narrowing its performance gap with Deepseek R1 overall. This reflects b... | https://arxiv.org/abs/2505.16660v1 |
permits multiple error types per problem, merely counting labels fails to capture intrinsic relationships between error categories. To address this, we further analyzed co -occurrence patterns among error labels, visualizing the results as a heatmap (see Figure 7). Figure 7. Co-occurrence Network Map of Error Labels As... | https://arxiv.org/abs/2505.16660v1 |
DeepSeek R1, Qwen - Plus) consistently outperformed 32B -parameter models in overall accuracy. This performance gap widened significantly in high -difficulty Level 3 –4 problems. This phe nomenon confirms the critical role of parameter scale effects in complex reasoning tasks. Among 32B -parameter models, those trained... | https://arxiv.org/abs/2505.16660v1 |
Our research also have some limitations . Firstly, t he dataset is derived solely from the Ten Mathematical Classics , covering Han to Tang Dynasty mathematics. Peak achievements of Chinese mathematics during the Song -Yuan -Ming periods (e.g., binomial theorems, trigonometric functions, Tianyuan Shu [天元术 ], Duoji Shu ... | https://arxiv.org/abs/2505.16660v1 |
J., Zhang, J., … Wang, Z. (2024). ChatGLM: A Family of Large Language Models from GLM -130B to GLM -4 All Tools (arXiv:2406.12793). arXiv. https://doi.org/10.48550/arXiv.2406.12793 Guo, S. C., & Liu, D. (1998). Suan jing shi shu[ 算经十书 ]. Liaoning Education Press. Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basar... | https://arxiv.org/abs/2505.16660v1 |
May 20, 2025, from https://ctext.org/zh Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. -A., Lacroix, T., Roziè re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., & Lample, G. (2023). LLaMA: Open and Efficient Foundation Language Models (arXiv:2302.13971). arXiv. https://doi... | https://arxiv.org/abs/2505.16660v1 |
得[[1]]分,得[[2]]分，你可以参考如下评分等级 :1分题为直 观的数学计算，只需适用简单的四则运算可迅速解决 \n2分 题多为四则运算的应用，包括简单的求周长和面积等 \n3分 题目是更加复杂的应用，需要结合历史知识并使用初次方 程等较高级的技术 \n4分题为更复杂的数学问题，可能涉及 到几何、代数或数论等领域的综合知识，或者需要二元、 二次以上方程解决 ：请根据以上逻辑进行判断。这道题目 是:{text} Problem Type Annotation qwen -plus- 2025 -04-28 现在将给你一道来自中国古代典籍的数学问题。请你给出这 道题目所涉及的数学方法，如：基础四则运算、体积计算、 面积计算、几何、... | https://arxiv.org/abs/2505.16660v1 |
arXiv:2505.16661v1 [cs.CL] 22 May 2025A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP Issey Sukeda1,2, Takuro Fujii*, Kosei Buma1,3, Shunsuke Sasaki1,2, Shinnosuke Ono1,2, 1EQUES Inc.,2The University of Tokyo,3University of Tsukuba, Correspondence: issey.sukeda@eques.co.jp Abstract ... | https://arxiv.org/abs/2505.16661v1 |
real-world operational tasks, such as document standardization and terminology nor- malization. To evaluate pharmaceutical reasoning and gener- ation capabilities, we introduce three novel bench- marks: (1) YakugakuQA (§3.2): a multiple-choice QA dataset based on the Japanese National Pharmacist Examination; (2) Nayose... | https://arxiv.org/abs/2505.16661v1 |
and adapted with medical con- tinual pretraining and supervised fine-tuning using curated English medical corpus. It demonstrates strong performance in MedQA (Jin et al., 2020), making it a prominent example of an open medi- cal LLM. The work is further extended by Open Meditron Initiative2. In contrast, our work focus... | https://arxiv.org/abs/2505.16661v1 |
tifying a chemical reaction depicted in the image. However, such image-based questions are excluded from our experiments, as our study focuses on LLMs designed for text input. The number of ques- tions by year and category used in our experiments 3https://yakugakulab.info/ 3 Benchmark Format Main Skill Source #Examples... | https://arxiv.org/abs/2505.16661v1 |
statements are consistent either ex- plicit or implicit. Some examples are clear-cut (e.g., numerical mistakes, see Figure 4), while others re- quire pharmacological reasoning or recognition of subtle semantic contradictions. The final dataset includes 200 examples, synthe- sized with an LLM to balance clarity and real... | https://arxiv.org/abs/2505.16661v1 |
sured based on exact match. 5.2 Quantitative results Table 4 shows the accuracy of each model on each benchmark. While GPT-4o achieved the highest accuracy overall, as expected from a frontier com- mercial LLM, our domain-specific model consis- tently outperformed both Meditron and the general- purpose Japanese model a... | https://arxiv.org/abs/2505.16661v1 |
for option “1” was the lowest among all choices (Figure 5b). Single vs. Multiple-Choice Question. GPT-4o exhibited a 4.4% higher error rate on multiple- choice questions compared to single-answer ques- tions (Figure 5c). Question category. Figure 5d shows that error rates for chemistry and physics are around 25%, while... | https://arxiv.org/abs/2505.16661v1 |
51.5 72.2 72.5 84.4 76.4 68.7 62.8 70.0 73.6 GPT-4o 94.4 76.1 80.9 83.4 92.1 88.7 81.8 72.6 78.6 83.6 o1-preview 93.3 88.3 88.1 83.3 93.2 90.8 85.0 89.1 84.5 87.9 JPHARMATRON -7B /2B tokens 80.9 28.4 55.9 66.6 71.5 55.7 55.1 55.2 58.6 60.7 JPHARMATRON -7B /10B tokens 70.8 19.3 53.6 57.3 66.9 46.2 48.8 51.7 55.3 54.8 JP... | https://arxiv.org/abs/2505.16661v1 |
still lag clearly behind commer- cial counterparts (Table 5). As a next step, it is essential to evaluate how much performance can be improved in targeted subject areas, depending on the intended application of the model, by sim- ply incorporating a substantial amount of relevant training data. For the lower-performing... | https://arxiv.org/abs/2505.16661v1 |
sep- arately released an instruction-style (SQuAD (Ra- jpurkar et al., 2016)-type) variant of NayoseQA, which is not included in the main results but mayserve as a valuable resource for future work on more realistic applications. Limitations of SogoCheck SogoCheck is currently limited in scale, with only a small number... | https://arxiv.org/abs/2505.16661v1 |
Katherine Lee, Ben- jamin Lee, Eric Li, Music Li, Wei Li, YaGuang Li, Jian Li, Hyeontaek Lim, Hanzhao Lin, Zhongtao Liu, Frederick Liu, Marcello Maggioni, Aroma Mahendru, Joshua Maynez, Vedant Misra, Maysam Moussalem, Zachary Nado, John Nham, Eric Ni, Andrew Nys- trom, Alicia Parrish, Marie Pellat, Martin Polacek, Alex... | https://arxiv.org/abs/2505.16661v1 |
Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Un- derstanding. Proceedings of the International Con- ference on Learning Representations (ICLR) . Kexin Huang, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W Coley, Cao Xiao, Jimeng Sun, and Marinka Z... | https://arxiv.org/abs/2505.16661v1 |
Neural Information Processing Systems , 35:19523–19536. Issey Sukeda. 2024. Development and bilingual evalua- tion of Japanese medical large language model within reasonably low computational resources. arXiv preprint arXiv:2409.11783 . Issey Sukeda, Risa Kishikawa, and Satoshi Kodera. 2024a. 70B-parameter large langua... | https://arxiv.org/abs/2505.16661v1 |
that must be addressed to ensure responsible development and deployment. Importantly, the model may still generate fac- tually incorrect or misleading content. We rec- ommend to further finetune our model with the company’s real data and conduct additional use- case alignment and testing before deploying it in real-wor... | https://arxiv.org/abs/2505.16661v1 |
33 23 28 36 31 18 59 250 Table 6: The number of questions used in our experiments by year and category. The questions that include images have been excluded from the original NPLE. calcitonin gene-related peptide (CGRP)? Please select exactly one from the options 1, 2, 3, 4, or 5. 1: Basiliximab 2: Trastuzumab 3: Benra... | https://arxiv.org/abs/2505.16661v1 |
pus for the pharmaceutical domain by leveraging a multi-stage filtering pipeline built upon large lan- guage models (LLMs) and trained classifiers. Fol- lowing SmolLM2 (Allal et al., 2025), the overall procedure consists of three steps: 1.We first sampled a subset of documents from the Common Crawl dataset (CC100). A h... | https://arxiv.org/abs/2505.16661v1 |
poor instruction- following capabilities. As a result, these mod- els struggle to answer multiple-choice questions correctly, rendering them ineffective for standard benchmark evaluations which rely heavily on such tasks. Instead of applying supervised fine-tuning (SFT), which can be resource-intensive and require care... | https://arxiv.org/abs/2505.16661v1 |
R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO Huanjin Yao2,3*, Qixiang Yin4*, Jingyi Zhang1, Min Yang2, Yibo Wang3, Wenhao Wu5 Fei Su4, Li Shen1, Minghui Qiu2, Dacheng Tao1, Jiaxing Huang1 1Nanyang Technological University2ByteDance3Tsinghua University 4Beijing Univer... | https://arxiv.org/abs/2505.16673v1 |
measure of 𝐽𝑀is3𝑎, calculate the value of𝑏.𝑄𝑆!𝑄=𝐼,𝑇 𝑄!=𝐼",𝑇 𝑄#=𝐼,𝑇"𝑄"𝑆!!𝑄#𝑆!"𝑄$𝑆!#𝑸Question (Image-Text)𝑺𝑸 Solution SpaceSemantically Consistent Transformation 𝑄$=𝐼",𝑇"(a) Explore and share diverse reasoning trajectories over expanded question space(b) Reward Curve (Left) and Valid Advantage ... | https://arxiv.org/abs/2505.16673v1 |
a successful reasoning response and thus mitigates the sparse rewarding issue as illustrated in the left curve of Fig. 1 (b). (2) Share-GRPO allows the model to explore diverse reasoning trajectories from the expanded question space and 2 shares the discovered reasoning trajectories, ultimately mitigating the advantage... | https://arxiv.org/abs/2505.16673v1 |
rule-based reward functions to enhance the reasoning abilities of MLLMs, such as geometric understanding and spatial perception. Unlike these methods, our ShareGRPO explores information sharing for MLLM reasoning reinforcement learning to mitigate sparse reward and advantage vanishing issues. 2.3 Information Sharing in... | https://arxiv.org/abs/2505.16673v1 |
samples with large magnitudes of advantages and reuse them in RL process, while MM-Eureka [ 5] employs an online filtering strategy to remove the samples with zero advantage. Different from the prior works, our Share-GRPO effectively addresses both of these two challenges by exploring and sharing diverse reasoning traj... | https://arxiv.org/abs/2505.16673v1 |
specific prompt to the corresponding textual prompt, providing contextual guidance aligned with the visual modification: Qonline={τ(ϕ(Tori)), ψ(Iori)}. (4) Solution Space Expansion. With the expanded question space Q={Q1, Q2, ..., Q m}, Share-GRPO enables to explore diverse reasoning trajectories in an enlarged solutio... | https://arxiv.org/abs/2505.16673v1 |
to examine the impact of each design in Share-GRPO. Sec. 4.4 provides more discussion and analysis of Share-GRPO. More details are elaborated in the subsequent subsections. 6 Table 1: Main Results. To examine the effectiveness of Share-GRPO, we compare our R1-ShareVL which is trained by Share-GRPO without cold-start su... | https://arxiv.org/abs/2505.16673v1 |
ThinkLite-7B drops -0.2% and -5.5% on MMStar and MMMU, respectively. In contrast, our R1-ShareVL-7B model achieves a +3.1% improvement on MMStar and comparable accuracy on MMMU, demonstrating Share-GRPO’s generalization capability in enhancing reasoning across diverse tasks. When scaling our method to larger models (i.... | https://arxiv.org/abs/2505.16673v1 |
complementarity between Share-GRPO and Dynamic Sampling. Method MathVista MMStar MMMU Avg. GRPO + Dynamic Sampling 73.6 65.7 56.1 65.1 Share-GRPO 75.4 67.0 58.1 66.8 Share-GRPO + Dynamic Sampling 75.9 66.7 59.0 67.2 Hyperparameter studies of Share GRPO. We study the impact of the number of question variant min Semantic... | https://arxiv.org/abs/2505.16673v1 |
model accurately interprets the question and arrives at the correct answer, showing strong performance in symbolic reasoning and function analysis. This highlights the capability of Share-GRPO to guide the model toward precise and coherent solutions in mathematically demanding tasks. 5 Conclusion In this paper, we prop... | https://arxiv.org/abs/2505.16673v1 |
aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages 24185–24198, 2024. [12] Dongchen Lu, Yuyao Sun, Zilu Zhang, Leping Huang, Jianliang Zeng, Mao Shu, and Huo Cao. Internvl- x: Advancing and accelerating internvl series with efficien... | https://arxiv.org/abs/2505.16673v1 |
Ren Lu, Thomas Mesnard, Johan Ferret, Colton Bishop, Ethan Hall, Victor Carbune, and Abhinav Rastogi. Rlaif: Scaling reinforcement learning from human feedback with ai feedback. 2023. [28] Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, et al. Rlhf-... | https://arxiv.org/abs/2505.16673v1 |
processing systems , 30, 2017. [43] Matteo Hessel, Hubert Soyer, Lasse Espeholt, Wojciech Czarnecki, Simon Schmitt, and Hado Van Hasselt. Multi-task deep reinforcement learning with popart. In Proceedings of the AAAI Conference on Artificial Intelligence , volume 33, pages 3796–3803, 2019. [44] Jakob Foerster, Ioannis ... | https://arxiv.org/abs/2505.16673v1 |
Chang, Michel Galley, and Jianfeng Gao. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 , 2023. [60] Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, et al. Are we on the right way f... | https://arxiv.org/abs/2505.16673v1 |
SPaRC: A Spatial Pathfinding Reasoning Challenge Lars Benedikt Kaesberg∗, Jan Philip Wahle∗, Terry Ruas, Bela Gipp University of Göttingen, Germany ∗{l.kaesberg, wahle}@uni-goettingen.de Dataset hf.co/datasets/lkaesberg/SPaRC Code github.com/lkaesberg/SPaRC Webpage sparc.gipplab.org Abstract Existing reasoning datasets... | https://arxiv.org/abs/2505.16686v1 |
taneously. This often involves revising previous hypotheses where a single wrong step can irrevoca- bly lead to the wrong path. We provide 500 train and 500 test puzzles of different sizes and difficulty degrees from 1 (very easy) to 5 (very hard). Experiments with three instruction-tuned mod- els, four reasoning model... | https://arxiv.org/abs/2505.16686v1 |
simple scenarios, the most advanced rea- soning models fail. However, ARC-AGI does not require step -by-step planning or following discrete rules. VisualPuzzles (Song et al., 2025) presents algorithmic, analogical, and spatial riddles, but every task is multiple choice, so the model is not constructing individual solut... | https://arxiv.org/abs/2505.16686v1 |
stars are allowed. Edge Count (Triangles): The solution path must touch the number of edges shown by the triangles in the cell, e.g., two triangles mean the path must touch exactly two edges of that cell. Shape Fitting (Polyominoes): If a cell contains a polyomino (poly), the solution path must enclose a region that ma... | https://arxiv.org/abs/2505.16686v1 |
score, which we then sta- tistically normalize onto a standardized 1 (easiest) to 5 (hardest) scale (see Appendix D for calculation specifics). As our later experiments with humans and reasoning models will demonstrate, this dif- ficulty estimate is pretty robust. The distribution of difficulties of SPaRC can be found ... | https://arxiv.org/abs/2505.16686v1 |
fallacies, and misinterpreting grid representations (Huang and Chang, 2022; Turpin et al., 2023). Difficulty Level We decompose the results in Figure 3 by difficulty. We compare the best model (o4-mini) against human performance. Humans achieve 100% accuracy at difficulty level 1, while o4-mini reaches 47.7%, showing i... | https://arxiv.org/abs/2505.16686v1 |
model-constructed paths and their rea- soning tokens to shed light on why reasoning mod- els fail to solve puzzles. Path Errors We analyze common errors in con- structing a valid path (ignoring rules to solve the game for now). We assess five error types for all 5 Subset -50 0 50 100 Δ Accuracy (%) -50 0 50 100 Δ Accur... | https://arxiv.org/abs/2505.16686v1 |
than the larger reasoning model R1 70B. Reasoning models have higher accuracy despite similar basic path errors, suggesting successful path construction is only the first hurdle. Across models, the most common error is Rule Cell Crossing , indicating frequent vi- olations by paths moving through rule cells rather than ... | https://arxiv.org/abs/2505.16686v1 |
points for level 1 puzzles (easy), but only 2.3 points for level 4 and 5 (difficult ones). This shows that our puzzles cannot be easily solved by just increasing the computation, but the reasoning steps have to get more sophisticated and have to adjust according to the difficulty level. Higher results for larger kgive ... | https://arxiv.org/abs/2505.16686v1 |
more explicitly. This ad- justment improved o4-mini’s accuracy from 15.8% to 21.0% and reduced path errors, with Rule CellDifficulty Level 1 2 3 4 5 Hum. Acc. (%) 100 % 100 % 100 % 94.4 % 94.5 % Hum. Avg. (s) 10.7 18.3 26.7 60.7 131.5 Hum. Mdn. (s) 7.1 13.7 15.6 28.8 85.6 QwQ Acc. (%) 20.9% 5.9% 2.5% 1.2% 0.0% QwQ #Tok... | https://arxiv.org/abs/2505.16686v1 |
requiring spatial and symbolic reasoning. We evaluated puzzles with six human annotators, three instruction-tuned models (GPT-4.1, Gemma 3, Qwen 2.5), and four reasoning models (o4-mini, o3-mini, QwQ, R1). Humans achieved a 98% accu- racy. The best reasoning model, o4-mini, reached only 16%. Performance was drastically... | https://arxiv.org/abs/2505.16686v1 |
partially supported by the Lower Saxony Ministry of Science and Culture and the VW Foundation. Many thanks to Andreas Stephan, Tianyu Yang, Zeinab Taghavi, and Annika Schulte- Hürmann for their thoughtful discussions and feed- back. 9 References Zachary Abel, Jeffrey Bosboom, Michael Coulombe, Erik D. Demaine, Linus Ha... | https://arxiv.org/abs/2505.16686v1 |
questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natu- ral Language Processing , pages 2383–2392, Austin, Texas. Association for Computational Linguistics. David Rein, Betty Li Hou, Asa Cooper Stickland, Jack- son Petty, Richard Yuanzhe Pang, Julien Dirani, Ju- ... | https://arxiv.org/abs/2505.16686v1 |
engineer- ing with chatgpt. ArXiv preprint , abs/2302.11382. Junjie Ye, Xuanting Chen, Nuo Xu, Can Zu, Zekai Shao, Shichun Liu, Yuhan Cui, Zeyang Zhou, Chao Gong, Yang Shen, Jie Zhou, Siming Chen, Tao Gui, Qi Zhang, and Xuanjing Huang. 2023. A comprehen- sive capability analysis of gpt-3 and gpt-3.5 series models. ArXi... | https://arxiv.org/abs/2505.16686v1 |
Sgrid) is weighted most heavily. Finally, to produce a standardized and inter- pretable difficulty score (typically ranging from 0 to 5), the raw score ( Sraw) is normalized. This is achieved by: 1.Calculating the Z-score of Srawrelative to a pre-determined normal distribution, charac- terized by a mean ( µ= 12.06) and... | https://arxiv.org/abs/2505.16686v1 |
solution path must pass through all dots present on its segments. (a) Unsolved Gaps puzzle. (b) Solved Gaps puzzle. Figure 12: Example of the Gaps rule. The solution path cannot cross specific marked edges on the grid. (a) Unsolved Stones puzzle. (b) Solved Stones puzzle. Figure 13: Example of the Stones rule. The solu... | https://arxiv.org/abs/2505.16686v1 |
solving puzzles from the game ’The Witness’. Your task is to solve the following puzzle by finding a valid line from the Start Node to the End Node. 16 GRID DEFINITION: - The puzzle involves a grid of {grid_size[’width’]}x{grid_size[’height’]} cells. - COORDINATE SYSTEM: Nodes are indexed (x, y). Node (0,0) is the top-... | https://arxiv.org/abs/2505.16686v1 |
Triangle with count 3 - ’D-X’ Triangle with count 4 - ’P-X-Y’: Positive polyshape of color X and shape ID Y - ’Y-X-Y’: Negative polyshape (ylop) of color X and shape ID Y COLOR CODES: R=red, B=blue, G=green, Y=yellow, W=white, O=orange, P=purple, K=black {example_section} PUZZLE GRID: {grid_str} POLYSHAPE DEFINITIONS: ... | https://arxiv.org/abs/2505.16686v1 |
and shape ID Y * ‘Y-X-Y‘: **Negative Polyshape** (ylop) of color X and shape ID Y **Color Codes:** R=Red, B=Blue, G=Green, Y=Yellow, W=White, O=Orange, P=Purple, K=Black ## Detailed Solving Rules The drawn path must satisfy **ALL** applicable constraints: 1. **Path Constraints:** 18 * Path **MUST** start at ‘S‘ and end... | https://arxiv.org/abs/2505.16686v1 |
a valid line from the Start Node to the End Node. The image shows a Witness puzzle grid of size {grid_size[’width’]*2}x{grid_size[’height’]*2}. In this puzzle: - The solution is a continuous line from the start circle to the end marker - The line travels along grid edges, connecting adjacent nodes horizontally or verti... | https://arxiv.org/abs/2505.16686v1 |
to (2,0) to reach the dot at (1,0) and surround the 3 count triangle. We then draw a line to (2,2) here we go down to touch the third side of the triangle cell and therefore validate the 3 count triangle. We continue down to (2,6) to validate the polyshape 112 and also the green star with the green polyshape After this... | https://arxiv.org/abs/2505.16686v1 |
shown in percent (%). I.2 Path Metrics Model Incorrect Start/End Disconnected Line Intersecting Line Rule Cell Crossing Invalid Path Reasoning o4-mini 3.8% 27.6% 31.2% 51.2% 59.2% o3-mini 3.0% 13.2% 8.0% 56.2% 63.2% QwQ 32B 1.6% 26.2% 30.8% 70.0% 76.4% R1 70B 10.2% 52.4% 35.8% 57.6% 82.2% Instruction GPT-4.1 53.8% 87.0... | https://arxiv.org/abs/2505.16686v1 |
go near there. Similarly, row 1 has ’G’s at 2 and 5, but the path goes through row 1, columns 0 and 1, which are ’+’, so that’s okay. ... Yes, thispath should work. Figure 19: Analysis of puzzle 80a59619e323acba with an incorrect solution attempt by DeepSeek R1 Llama 70B Distill. The model tends to commit to a sequence... | https://arxiv.org/abs/2505.16686v1 |
(1,1) — but(1,1) isarulecell, socan’t gothere. So instead, go right to (1,2), which is a ’.’ that must be passed through. So from (0,2) to (1,2). ... Wait, butthelinemust pass through (2,4). So perhaps from (1,2), go down to (2,2), then right to (2,3), then down to (2,4), which is a ’.’. ... So path so far: (0,2) →(1,2... | https://arxiv.org/abs/2505.16686v1 |
Right Panel: Line chart displaying the Accuracy (%) against puzzle Difficulty Level (1-5). The standard o4-mini Zero-Shot achieves a significantly higher overall accuracy ( 12.6% , blue dotted line) compared to o4-mini Vision (5.6% , orange dotted line), outperforming it at nearly all difficulty levels. L.2 Alternative... | https://arxiv.org/abs/2505.16686v1 |
click Show Solution or Skip Puzzle to continue. Once you have completed all 50 puzzles, please e-mail the annotated file back to us. By sending the file back to us, you agree that we can publish your annotations anonymously. This includes solve time, required attempts, and solution path. Rules The line must connect Sta... | https://arxiv.org/abs/2505.16686v1 |
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence Gouki Minegishi1Hiroki Furuta1Shohei Taniguchi1Yusuke Iwasawa1Yutaka Matsuo1 Abstract Transformer-based language models exhibit In- Context Learning (ICL), where predictions are made adaptively based on context. While prior work link... | https://arxiv.org/abs/2505.16694v1 |
LLMs (Wang et al., 2022; Merullo et al., 2024), and engaging in intricate interactions with multi-head attention (Singh et al., 2024). However, the copy mechanism as described in the induc- tion head explains only a fraction of the few-shot ICL. Let us consider, for instance, the following ICL scenario in a Country-to-... | https://arxiv.org/abs/2505.16694v1 |
multi-head model, which is a more practical setting; sudden jumps in accuracy become less apparent, and different heads can still specialize in par- allel — for instance, one head may converge on a particular circuit, while another becomes a different one. Although this parallel specialization leads to smoother accurac... | https://arxiv.org/abs/2505.16694v1 |
head, and the earlier layer is referred to as the previous token head. Previous token head attends to and copies the preceding token into the current token. When few-shot examples are present in the context, it chunks each (x, ℓ)pair into a single token. Induction heads then perform a match-and-copy operation, matching... | https://arxiv.org/abs/2505.16694v1 |
mean vector µk, whose entries are drawn independently from N(0,1/D). For an itemxiassigned to class k, we add noise η(sampled from the same distribution) scaled by ϵ, giving xi=µk+ϵ η√ 1+ϵ2, where ϵgoverns within-class variation and the denominator ensures ∥xi∥ ≈1. Finally, each class is linked to one of L labels, with... | https://arxiv.org/abs/2505.16694v1 |
are as follows: the first accuracy plateau occurs at around 30–40%, the second at approxi- mately 75%, and the final phase reaches 100%. To clearly these three phases, we define the following metric: ∆Accuracy =Accuracy t+ ∆t −Accuracy (t), where tdenotes the optimization step and we set ∆t= 100 . In Figure 3, we plo... | https://arxiv.org/abs/2505.16694v1 |
3 (red), defined by ∆Accuracy (Figure 3). Each metric shifts cleanly at the phase boundaries, demonstrating a close correspondence between accuracy improvements and circuit-level transformations. ship (i.e., task inference), the model can produce correct answers for the query. Once the model learns this circuit, it ach... | https://arxiv.org/abs/2505.16694v1 |
becomes usable, the binary choice can potentially be narrowed fur- ther. This occurs when one of the labels corresponding to 5 Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence 103 104 105 Steps0.00.20.40.60.81.0 AccuracyK=8 K=16 K=32 Theoretical Accuracy Figure 5. Comparison of the... | https://arxiv.org/abs/2505.16694v1 |
this work, we explore how these data properties affect the development of circuits in our ICML setting, with the aim of advancing our understand- ing of the multi-phase emergence of these circuits. As mentioned in Section 3, the variables capturing the char- acteristics of the data include the number of tasks T, the nu... | https://arxiv.org/abs/2505.16694v1 |
Following the results of Chan et al. (2022), higher values of ϵmake it more difficult for the model to memorize the (x, ℓ)pairs in its weights, and thus it shifts its focus toward leveraging the context. The observation that NCC is skipped entirely when ϵ= 1 aligns with this trend. Although SCC is a circuit that uses t... | https://arxiv.org/abs/2505.16694v1 |
dynamics between single-head (blue) and multi-head (orange) attention models (left). The multi- head model exhibits smoother accuracy improvements, without the distinct learning phases observed in the single-head model. On the right, the attention maps for the two heads in the multi-head model are visualized. Head 1 sp... | https://arxiv.org/abs/2505.16694v1 |
in induction heads. While both induction heads and our Full-Context Circuits (FCC) chunk contextual (x, ℓ)pairs into a single token in the first layer, the second layer diverges: induction heads retrieve only a label, whereas FCC further aggregates (Chunk Example → Label Attention in Table 1). This shared mechanism in ... | https://arxiv.org/abs/2505.16694v1 |
corresponding review tokens. Figure 10 shows that the Chunk Example metric is higher 1https://huggingface.co/datasets/stanfordnlp/sst2 2https://huggingface.co/openai-community/gpt2-xlin early layers, while Label Attention dominates later lay- ers—mirroring our two-layer model’s progression from chunk example to label f... | https://arxiv.org/abs/2505.16694v1 |
A., Mavor-Parker, A. N., Lynch, A., Heimersheim, S., and Garriga-Alonso, A. Towards automated circuit discovery for mechanistic interpretability, 2023b. URL https://arxiv.org/abs/2304.14997 . Crosbie, J. and Shutova, E. Induction heads as an essential mechanism for pattern matching in in-context learning. arXiv preprin... | https://arxiv.org/abs/2505.16694v1 |
pattern analysis and machine intelligence , 44(9):5149–5169, 2021. Kim, J. and Suzuki, T. Transformers learn nonlinear fea- tures in context: Nonconvex mean-field dynamics on the attention landscape. arXiv preprint arXiv:2402.01258 , 2024. Merullo, J., Eickhoff, C., and Pavlick, E. Circuit component reuse across tasks ... | https://arxiv.org/abs/2505.16694v1 |
E., Jones, A., Cunningham, H., Turner, N. L., McDougall, C., MacDiarmid, M., Freeman, C. D., Sumers, T. R., Rees, E., Batson, J., Jermyn, A., Carter, S., Olah, C., and Henighan, T. Scaling monosemanticity: Ex- tracting interpretable features from claude 3 sonnet. Transformer Circuits Thread , 2024. URL https: //transfo... | https://arxiv.org/abs/2505.16694v1 |
the first attention layer encodes each (x, ℓ)pair into a single token, while the second layer strongly attends to one of these pairs, effectively implementing the match-and-copy mechanism characteristic of an induction head. Notably, our setting thus subsumes the standard induction head experiments proposed in Reddy (2... | https://arxiv.org/abs/2505.16694v1 |
improvement, sequentially discovering and leveraging the circuits corresponding to each phase. This highlights the dynamic nature of the full model’s training process, where it incrementally constructs and refines the required circuits during training. 103 104 105 106 Optimization Steps0.00.20.40.60.81.0Accuracy Phase ... | https://arxiv.org/abs/2505.16694v1 |
drop in frequency beyond the highest-ranked elements. 0 20 40 60 80 100 Rank k0.00.20.40.60.81.0f(k)Rank-Frequency Distributions for Different α Values (f(k)=k−α) =0 =0.25 =0.5 =0.75 =1.0 =1.25 Figure 14. Rank-frequency distributions for different values of the power-law exponent α, following the Zipfian distribution f... | https://arxiv.org/abs/2505.16694v1 |
values across both Layer 1 and Layer 2. This indicates that it primarily performs token-level copying operations, forming an NCC. In contrast, Head 2 exhibits a different pattern. As training progresses, the chunk example metric increases in Layer 1, while the label attention metric becomes dominant in Layer 2, forming... | https://arxiv.org/abs/2505.16694v1 |
much easier for the model to learn a circuit that leverages the context, eliminating the need for intermediate phases. (b)Attention maps of a two-layer, attention-only Transformer with N= 16 (context length = 33) at 100% accuracy. The first layer (left) shows a chunk example attention pattern, whereas the second layer ... | https://arxiv.org/abs/2505.16694v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.