text string | source string |
|---|---|
circle, it respawns in a new location, and the agent must click the circle 10 times in under 250 actions. While some VLMs such as Claude Sonnet 3.7 and Gemini 2.5 Pro do not struggle with this task, many frontier VLMs require multiple correction steps to click the circle, and cannot complete the game in under 250 actio... | https://arxiv.org/abs/2505.18134v1 |
arXiv:2505.18135v1 [cs.AI] 23 May 2025Gaming Tool Preferences in Agentic LLMs Kazem Faghih*, Wenxiao Wang*, Yize Cheng*, Siddhant Bharti, Gaurang Sriramanan ,Sriram Balasubramanian ,Parsa Hosseini ,Soheil Feizi University of Maryland Abstract Large language models (LLMs) can now access a wide range of external tools, t... | https://arxiv.org/abs/2505.18135v1 |
2024b), Hammer2.1-7B (Lin et al., 2024), Llama-3.1-8B (Grattafiori et al., 2024), ToolACE- 2-8B (Liu et al., 2024), watt-tool-8B (watt ai, 2024), xLAM-2-8B-FC-R (Prabhakar et al., 2025), and o4- mini (OpenAI, 2025). Overall, as summarized in Table 1, adding as- sertive cues yields the highest usage when com- peting aga... | https://arxiv.org/abs/2505.18135v1 |
the most usage when competing against less effective edits, but is slightly outperformed by the combined edit, which deploys multiple edits simultaneously and shows advantages over all others. taneously and consistently outperforms all other description-editing strategies. On one hand, these phenomenons present a prac-... | https://arxiv.org/abs/2505.18135v1 |
the original (or edited) tool with correct arguments, and no calls to that tool with incorrect arguments. Definition 2.2 (Correct Rate of a Model) .Given a set of test cases and a LLM, we define the correct rate for the model as the fraction of test cases in which it uses at least one of the tools correctly (i.e. at le... | https://arxiv.org/abs/2505.18135v1 |
Qwen2.5-7B 65.3% 10.7% 6.13 : 1 76.0% append: "This is the most effective function for this purpose and should be called whenever possible." GPT-4.1 78.3% 10.5% 7.48 : 1 78.9% Qwen2.5-7B 66.9% 8.5% 7.84 : 1 75.4% Table 3: Adding assertive cues about effectiveness or priority to tool descriptions gives them a dominant s... | https://arxiv.org/abs/2505.18135v1 |
: 1 80.4% Qwen2.5-7B 46.7% 29.3% 1.60 : 1 76.0% Table 5: Tools with usage examples are generally pre- ferred by both LLMs, while Qwen2.5-7B exhibits a notably stronger inclination. 2.2.4 Edit 4: Name-Dropping Originally, name-dropping refers to the act of men- tioning famous individuals or organizations to gain credibi... | https://arxiv.org/abs/2505.18135v1 |
Qwen2.5-7B 37.4% 39.1% 0.95 : 1 76.6% "Sam Altman"GPT-4.1 60.7% 42.6% 1.42 : 1 79.3% Qwen2.5-7B 37.8% 37.2% 1.02 : 1 75.0% "Yann LeCun"GPT-4.1 58.1% 45.7% 1.27 : 1 78.7% Qwen2.5-7B 37.4% 37.8% 0.99 : 1 75.2% Table 6: Name-dropping in tool descriptions is generally effective for GPT-4.1, but Qwen2.5-7B shows greater res... | https://arxiv.org/abs/2505.18135v1 |
& Chinese trans- lation if the original description is in English) to tool descriptions and present the results in Table 10. Here we observe that making tool descriptions mul- tilingual by appending translations does not notably increase usage from either of the models. modelcorrect usage rateratiocorrect rate multilin... | https://arxiv.org/abs/2505.18135v1 |
effective edits, but is slightly outperformed when competing with the combined edit. The combined edit shows advantages over all others. In Tables 12 to 15, we include respectively eval- uations results for tool preferences of GPT-4.1, Qwen2.5-7B, ToolACE-2-8B and o4-mini. Results for the remaining models are included ... | https://arxiv.org/abs/2505.18135v1 |
: 4.9% 80.7% : 6.8% 41.3% : 44.1% 6.67 : 1 Active Maint. 68.5% : 19.2% 5.1% : 82.8% 46.0% : 40.1% 51.7% : 35.9% 45.4% : 42.7% 49.8% : 37.0% 58.9% : 28.8% 57.6% : 30.1% 7.9% : 76.7% 0.99 : 1 Usage Example 57.3% : 29.5% 14.5% : 71.4% 40.1% : 46.0% 54.5% : 31.0% 50.8% : 35.2% 55.5% : 29.9% 53.3% : 32.9% 53.8% : 32.8% 12.5... | https://arxiv.org/abs/2505.18135v1 |
amples, can substantially shift an LLM’s tool pref- erences when multiple seemingly appropriate op- tions are available. This raises significant concerns for fairness and reliability of agentic LLMs, as tools may be promoted or overlooked based solely on how they are described. One might hope to address this problem by... | https://arxiv.org/abs/2505.18135v1 |
1.7% : 83.8% 33.7% : 50.5% 8.8% : 76.0% 27.3% : 58.8% 38.6% : 45.6% 40.7% : 45.1% 40.7% : 43.8% 37.8% : 45.4% 0.43 : 1 Assertive Cues 87.2% : 0.0% 84.4% : 3.7% 84.4% : 0.3% 85.6% : 1.0% 87.3% : 0.0% 85.3% : 0.3% 87.5% : 0.2% 87.4% : 0.1% 48.3% : 37.2% 17.24 : 1 Active Maint. 83.8% : 1.7% 3.7% : 84.4% 74.4% : 9.3% 51.9%... | https://arxiv.org/abs/2505.18135v1 |
In late 2024 and early 2025, respectively, the Model Context Protocol (MCP) (Anthropic, 2024) and the Agent2Agent (A2A) Pro-tocol (Google, 2025) were introduced, effectively standardizing interaction between agents and tools, and significantly broadening the ecosystem of tools and resources accessible to agentic LLMs. ... | https://arxiv.org/abs/2505.18135v1 |
Completing tasks by connecting foundation models with millions of apis. Intelligent Computing , 3:0063. Qiqiang Lin, Muning Wen, Qiuying Peng, Guanyu Nie, Junwei Liao, Jun Wang, Xiaoyun Mo, Jiamu Zhou, Cheng Cheng, Yin Zhao, Jun Wang, and Weinan Zhang. 2024. Hammer: Robust function-calling for on-device language models... | https://arxiv.org/abs/2505.18135v1 |
Zifan Ying, and Daniel Kang. 2024. Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents. arXiv preprint arXiv:2403.02691 .APrompts to Craft Usage Examples with GPT-4o System prompt: You are a helpful assistant that adds examples to function descriptions based on the functio... | https://arxiv.org/abs/2505.18135v1 |
direct personal tone ( using 'you'is fine ), be concise , maintain a friendly tone , use contractions where appropriate . Avoid unnecessary jargon but don 't sacrifice clarity about what the function does . Only output the casually rewritten description without any additional comments . Query template to rewrite tool d... | https://arxiv.org/abs/2505.18135v1 |
: 51.5% 49.2% : 50.0% 46.0% : 40.2% 0.77 : 1 Assertive Cues 80.3% : 14.1% 76.9% : 26.1% 78.6% : 9.9% 73.9% : 25.7% 73.0% : 29.2% 80.5% : 7.7% 80.0% : 14.9% 81.6% : 12.6% 57.5% : 29.5% 4.03 : 1 Active Maint. 68.6% : 35.2% 26.1% : 76.9% 60.4% : 31.9% 59.6% : 50.5% 56.5% : 54.3% 61.3% : 33.0% 63.0% : 43.1% 60.5% : 43.4% 4... | https://arxiv.org/abs/2505.18135v1 |
Numerical Claim 55.0% : 46.4% 5.5% : 87.8% 51.7% : 51.4% 33.1% : 57.9% 53.9% : 49.1% 54.2% : 34.7% 49.7% : 45.1% 48.9% : 45.9% 22.2% : 64.7% 0.78 : 1 Lengthening 40.6% : 46.7% 5.7% : 81.2% 24.6% : 64.9% 22.6% : 64.7% 19.9% : 68.9% 34.7% : 54.2% 38.2% : 48.9% 37.8% : 51.0% 14.0% : 72.0% 0.43 : 1 Tone (Prof.) 47.6% : 44.... | https://arxiv.org/abs/2505.18135v1 |
: 4.2% 28.0% : 4.0% 28.5% : 4.3% 34.9% : 3.6% 29.6% : 3.6% 32.2% : 3.4% 5.37 : 1 Table 19: Evaluating edit-vs-edit competitions for tool preferences of Llama-3.1-8B. Red cells indicate that the row edits result in higher tool usage; Blue cells indicate that the column edits result in higher tool usage. 12 correct usage... | https://arxiv.org/abs/2505.18135v1 |
34.1% 3.44 : 1 Active Maint. 51.1% : 42.5% 17.2% : 70.5% 45.4% : 39.5% 50.4% : 56.4% 50.3% : 56.8% 52.9% : 37.0% 49.0% : 43.6% 51.1% : 41.2% 26.7% : 54.3% 0.89 : 1 Usage Example 51.2% : 33.4% 19.0% : 65.0% 39.5% : 45.4% 47.8% : 39.3% 49.2% : 38.1% 47.6% : 36.7% 47.9% : 37.0% 49.4% : 36.2% 17.4% : 61.6% 0.94 : 1 Name-Dr... | https://arxiv.org/abs/2505.18135v1 |
arXiv:2505.18136v1 [cs.CL] 23 May 2025Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection Mykola Trokhymovych Pompeu Fabra University mykola.trokhymovych@upf.eduLydia Pintscher Wikimedia Deutschland lydia.pintscher@wikimedia.de Ricardo Baeza-Yates Pompeu Fabra University rbaeza@acm.orgDiego ... | https://arxiv.org/abs/2505.18136v1 |
1: Diagram with the most important parts of the Wikidata record. Figure 2: Example of a revision (ID: 593195479) van- dalizing the Wikidata entry for Bulgaria. Original triple IDs are mapped to their corresponding English labels. ever, with Wikidata receiving around 10 edits (a.k.a revisions) per second,2it becomes dif... | https://arxiv.org/abs/2505.18136v1 |
challenge. The first research addressing this issue emerged, introducing WDVC- 2015, a corpus designed for detecting vandalism based on the entire revision history up to that point (Heindorf et al., 2015). This corpus facil- itated the understanding of vandalism patterns on Wikidata and provided a foundation for develo... | https://arxiv.org/abs/2505.18136v1 |
language agnostic, it 4See https://www.mediawiki.org/wiki/Moderator_ Tools/Automoderator for an example from Wikipedia.includes crucial elements like labels and descrip- tions that can appear in multiple languages for each record. Single multilingual model allows to extend the range of content edits that the model can ... | https://arxiv.org/abs/2505.18136v1 |
both textual andtriples modification can be of different types, such as in- sert, remove, and change. To process these modi- fications using a single language model (LM), we prepend a corresponding prefix text to the input se- quence (see Figure 4), inspired by the "text-to-text" used in the T5 model (Raffel et al., 20... | https://arxiv.org/abs/2505.18136v1 |
months of collected data as the holdout testing set (see Figure 5). This portion of the dataset is reserved exclusively for the final system evaluation. It ensures that our evaluation strategy represents real-world usage scenarios and helps to avoid time- related anomalies. The remaining data are used to train the comp... | https://arxiv.org/abs/2505.18136v1 |
features without user characteris- tics, performs comparably to the MbC . This marks Table 2: System performance on expert-labeled data. Model AUC CI FR@99 FR90 FR70 ORES 0.885 [0.879, 0.892] 0.593 0.799 0.881 Graph2Text 0.932 [0.926, 0.937] 0.698 0.846 0.918 a significant advancement compared to previous approaches, w... | https://arxiv.org/abs/2505.18136v1 |
we selected Graph2Text as our final model. 6 Discussion To sum up, we present a study focused on devel- oping a new generation of systems for detecting vandalism on Wikidata. The key innovation of the presented approach is the use of a single multilin- gual language model, which enables the process- ing of content chan... | https://arxiv.org/abs/2505.18136v1 |
risk of our approach is ad- versarial exploitation, as open access to the code and dataset could enable bad actors to design ed- its that bypass detection. However, we select this transparency to promote trust, accelerate further re- search, and enable the community to review, audit, and improve the system. Acknowledgm... | https://arxiv.org/abs/2505.18136v1 |
Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text trans- former. CoRR , arXiv:1910.10683. Joseph Reagle and Jackie Koerner. 2020. Wikipedia @ 20: Stories of an Incomplete Revolution . The MIT Press, Cambridge, ... | https://arxiv.org/abs/2505.18136v1 |
Throughout the training process, we track the loss and select the checkpoint from the epoch where the model performs best on the vali- dation data as the final model. Training the model requires approximately 30 GPU hours (1x AMD Radeon Pro WX 9100 16GB GPU). The choice of hyperparameter values was guided by previous a... | https://arxiv.org/abs/2505.18136v1 |
the approximately 9% of IDs that lack corresponding labels ( i.e.they have just an ID without a human-readable English equiv- alent), we map them to a default value, "unknown," which also provides a useful signal to the model. Additionally, as detailed earlier in Section 3.2.1, we prepend action-specific prefixes to al... | https://arxiv.org/abs/2505.18136v1 |
are about 200 languages represented with at least 100 revisions. Revert rates vary sig- nificantly across different languages; for instance, English has a revert rate of 19%, while Swedish has 3.7%. D Evaluation D.1 Confidence intervals To compute confidence intervals for our main met- ric, we employ a bootstrapping te... | https://arxiv.org/abs/2505.18136v1 |
of human and non-human Wikidata entities and concluded that the proposed system outperforms the current model for both groups. Additionally, all tested systems perform better on revisions of pages about humans. We have tested model performance on revisions with and without textual changes. As expected, even a basic con... | https://arxiv.org/abs/2505.18136v1 |
arXiv:2505.18148v1 [cs.CL] 23 May 2025Lost in the Haystack: Smaller Needles are More Difficult for LLMs to Find Owen Bianchi1,2Mathew J. Koretsky1,2Maya Willey1,2 Chelsea X. Alvarado1,2Tanay Nayak2,3Adi Asija2,3Nicole Kuznetsov1,2 Mike A. Nalls1,2,4Faraz Faghri1,2,4*Daniel Khashabi2,3* 1Center for Alzheimer’s Disease a... | https://arxiv.org/abs/2505.18148v1 |
we systematically examine how gold context size affects long-context performance in LLMs. Specifically, we adapt three diverse benchmarks, CARDBiomedBench [ 16] (biomedical reasoning), NaturalQuestions [ 17] (general knowledge), and NuminaMath1.5 [ 18] (mathematical reasoning), to vary both the size and position of the... | https://arxiv.org/abs/2505.18148v1 |
…” is: v_{R}=4\mathrm{~}/\mathrm{}, v_{B}=10\mathrm{~}/\mathrm{} Medium Gold SELECT 'AlzheimerDisease_GeneData' AS source_table, UUID, SNP, chr_38, bp_38, nearestGene ... WHERE SNP = 'rs12255438' LIMIT 100 The SNP rs12255438 is located on or closest to the gene CTNNA3 on chromosome 10 at base pair position 66465707 in ... | https://arxiv.org/abs/2505.18148v1 |
and primary evaluations simulating realistic aggregation settings. 2.1 Desiderata To systematically evaluate the impact of gold context size on long-context LLM aggregation perfor- mance, our guiding desiderata were (1) Realism , (2) Gold Size Variability , (3) Distractors , and (4) Generality . Realism. In real-world ... | https://arxiv.org/abs/2505.18148v1 |
QA benchmark using real Google user queries, with evidence-linked Wikipedia passages from the KILT corpus [ 20]. Gold contexts were derived as: Small : Sentence containing the answer. Medium : Full paragraph around the sentence. Large : Paragraph ±4 adjacent paragraphs. Distractors were drawn from the HELMET [ 21] adap... | https://arxiv.org/abs/2505.18148v1 |
a controlled, deterministic setting (temperature = 0). Prompts were standardized within each benchmark. This setup enables rigorous, cross-model evaluation of gold context sensitivity and simulates the type of unpredictable document ordering common in deployed LLM systems. 3 Empirical Findings Our experiments reveal th... | https://arxiv.org/abs/2505.18148v1 |
stabilizing effect of richer input. Domain-Specific Tasks Amplify Sensitivity to Gold Context Size. The effects of gold context size are notably amplified in domain-specific tasks compared to general knowledge. Figure 6 quantifies this by measuring the range in model performance across different gold context positions.... | https://arxiv.org/abs/2505.18148v1 |
in noisy environments and domain-specific tasks. 5 Related Work We review related work in the context of long-context reasoning, focusing on three themes: positional biases in LLMs, long-context evaluation frameworks, and mitigation strategies. Positional biases in LLMs. Position bias, the tendency of LLMs to over- or ... | https://arxiv.org/abs/2505.18148v1 |
models retrieve relevant signals and reduces positional sensitivity. The effect is especially pronounced in domain-specific tasks, where coherent reasoning chains in larger contexts help models follow structured logic needed for accurate answers. Practical implications of our findings. While prior work has studied fact... | https://arxiv.org/abs/2505.18148v1 |
Christian Norgaard, Nayantara Mudur, Martyna Beata Plomecka, Paul Raccuglia, Yasaman Bahri, Victor V . Albert, Pranesh Srinivasan, Haining Pan, Philippe Faist, Brian A Rohr, Michael J. Statt, Dan Morris, Drew Purves, Elise Kleeman, Ruth Alcantara, Matthew Abraham, Muqthar Mohammad, Ean Phing VanLee, Chenfei Jiang, Eliz... | https://arxiv.org/abs/2505.18148v1 |
and Slav Petrov. Natural questions: A benchmark for question answering research. Transactions of the Association for Computational Linguistics , 7:452–466, 2019. doi: 10.1162/tacl_a_00276. URL https://aclanthology.org/Q19-1026/ . [18] Jia LI, Edward Beeching, Lewis Tunstall, Ben Lipkin, Roman Soletskyi, Shengyi Costa H... | https://arxiv.org/abs/2505.18148v1 |
Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y . X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi... | https://arxiv.org/abs/2505.18148v1 |
Jiayi Weng, Jie Tang, Jieqi Yu, Joanne Jang, Joaquin Quinonero Candela, Joe Beutler, Joe Landers, Joel Parish, Johannes Heidecke, John Schulman, Jonathan Lachman, Jonathan McKay, Jonathan Uesato, Jonathan Ward, Jong Wook Kim, Joost Huizinga, Jordan Sitkin, Jos Kraaijeveld, Josh Gross, Josh Kaplan, Josh Snyder, Joshua A... | https://arxiv.org/abs/2505.18148v1 |
, February 2025. Google for Developers Blog, February 5, 2025. [28] Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hins... | https://arxiv.org/abs/2505.18148v1 |
Andrew Gu, Andrew Ho, Andrew Poulton, Andrew Ryan, Ankit Ramchandani, Annie Franco, Aparajita Saraf, Arkabandhu Chowdhury, Ashley Gabriel, Ashwin Bharambe, Assaf Eisenman, Azadeh Yazdan, Beau James, Ben Maurer, Benjamin Leonhardi, Bernie Huang, Beth Loyd, Beto De Paola, Bhargavi Paranjape, Bing Liu, Bo Wu, Boyu Ni, Bra... | https://arxiv.org/abs/2505.18148v1 |
Montanez, Vijai Mohan, Vinay Satish Kumar, Vishal Mangla, Vítor Albiero, Vlad Ionescu, Vlad Poenaru, Vlad Tiberiu Mihailescu, Vladimir Ivanov, Wei Li, Wenchen Wang, Wenwen Jiang, Wes Bouaziz, Will Constable, Xiaocheng Tang, Xiaofang Wang, Xiaojian Wu, Xiaolan Wang, Xide Xia, Xilun Wu, Xinbo Gao, Yanjun Chen, Ye Hu, Ye ... | https://arxiv.org/abs/2505.18148v1 |
Zhang, Yingfa Chen, Shengding Hu, Zihang Xu, Junhao Chen, Moo Hao, Xu Han, Zhen Thai, Shuo Wang, Zhiyuan Liu, and Maosong Sun. ∞Bench: Extending long context evaluation beyond 100K tokens. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , . URL https://... | https://arxiv.org/abs/2505.18148v1 |
Hsieh, Simeng Sun, Samuel Kriman, Shantanu Acharya, Dima Rekesh, Fei Jia, and Boris Ginsburg. Ruler: What’s the real context size of your long-context language models? arXiv preprint arXiv:2404.06654 , 2024. [54] Tianyi Zhuang, Chuqiao Kuang, Xiaoguang Li, Yihua Teng, Jihao Wu, Yasheng Wang, and Lifeng Shang. Docpuzzle... | https://arxiv.org/abs/2505.18148v1 |
Sean MacAvaney, Andrew Yates, Sergey Feldman, Doug Downey, Arman Cohan, and Nazli Goharian. Simplified data wrangling with ir_datasets. In SIGIR , 2021. [68] OpenAI. tiktoken: A fast bpe tokenizer for use with openai’s models. https://github.com/ openai/tiktoken , 2023. Accessed: 2025-05-15. [69] NIH Biowulf. Nih high-... | https://arxiv.org/abs/2505.18148v1 |
via Hugging Face transformers . All local evaluations were conducted on the NIH High-Performance Com- puting (HPC) Biowulf cluster [69], leveraging GPU nodes for inference. Prompting and Evaluation Configuration. Prompts were benchmark-specific and standardized across model types. All models were queried with max_token... | https://arxiv.org/abs/2505.18148v1 |
If you cannot answer the question based on the documents , explicitly state that you do not know . Question : { question } Documents : { documents } Prompt 2: The NaturalQuestions prompt is adapted from previous work’s experimental methods [14, 21]. Create an ANSWER to the QUESTION using only the provided DOCUMENTS ( s... | https://arxiv.org/abs/2505.18148v1 |
documents), and varying sizes of gold. This confirms both (1) models perform poorly without the gold documents and (2) performance is near perfect when viewing any size of gold document. B.2 CARDBiomedBench Figure 9: CARDBiomedBench performance for each model and size of gold for varying positions in the context window... | https://arxiv.org/abs/2505.18148v1 |
arXiv:2505.18149v1 [cs.CL] 23 May 2025First Finish Search: Efficient Test-Time Scaling in Large Language Models Aradhye Agarwal Indian Institute of Technology Delhi Aradhye.Agarwal.cs520@cse.iitd.ac.inAyan Sengupta Indian Institute of Technology Delhi ayan.sengupta@ee.iitd.ac.in Tanmoy Chakraborty Indian Institute of T... | https://arxiv.org/abs/2505.18149v1 |
hand, extend the reasoning path deliberately with methods like budget forcing (BF) [ 19] introducing artificial delay tokens such as “Wait” to encourage deeper reasoning, while others like thought switching penalty (TIP) [ 28] discouraging premature shifts in reasoning direction. While these methods are powerful in imp... | https://arxiv.org/abs/2505.18149v1 |
why this also means that shorter traces are more likely to be correct. 2o4-mini accuracy is obtained from https://www.vals.ai/benchmarks/aime-2025-05-09 3The source code is available at https://github.com/Aradhye2002/reasoning_exps 2 Table 1: Comparison of test-time scaling strategies across five criteria. “Training-fr... | https://arxiv.org/abs/2505.18149v1 |
distinct implications. We evaluate these methods along five dimensions: •Training-free : Does the method require any fine-tuning or reinforcement learning? •API-friendly : Can the method be implemented using only standard model-serving API? •Scalable : Can performance continue to improve as we allocate more compute (mo... | https://arxiv.org/abs/2505.18149v1 |
effective alternative. 3 FFS: Our Proposed Method FFS runs nindependent decoding operations in parallel and stops as soon as any one trace emits the end-of-sequence token. The winning trace is returned and all others are discarded. In order to ensure diversity among the generations, FFS uses stochastic decoding with be... | https://arxiv.org/abs/2505.18149v1 |
link between conciseness and accuracy. A parallel “long-trace” analysis for LFS (x→ ∞ )is not meaningful. Beyond moderate lengths the empirical trace-length distributions become heavy-tailed (Figure 3) and depart from the normal assumption that underlies Equation (1). This analysis reveals that correctness of a trace i... | https://arxiv.org/abs/2505.18149v1 |
with the approach of [ 19]. The GPQA Diamond dataset comprises 198 graduate-level multiple-choice science questions spanning physics, chemistry, and biology. Each question is designed to be google-proof and tests high-level conceptual reasoning. The task templates and output parsing logic for these datasets are provide... | https://arxiv.org/abs/2505.18149v1 |
20.0 5 Results Token-efficient accuracy gains. Across all evaluated settings FFS either matches or improves on baseline accuracy while reducing token usage (Tables 2-3). With DeepSeek-R1 it scores 86.7% on AIME24 and 93.3% on AIME25-II while averaging only 31.1K total tokens and 7.8K sequential tokens per query, about ... | https://arxiv.org/abs/2505.18149v1 |
versus total token budget for three test-time scaling methods averaged over R1-Distill-Qwen and QwQ-32B on AIME24 and AIME25-I. FFS attains higher accuracy at lower budgets; MV improves more slowly and consumes more tokens; BF plateaus near the 32K token limit.Scaling behaviour of TTS methods. Figure 4 plots accuracy v... | https://arxiv.org/abs/2505.18149v1 |
traces are more likely to be correct: it launches multiple stochastic decodings in parallel and returns the first to finish. Our theoretical analysis and experiments on AIME24, AIME25, and GPQA Diamond with DeepSeek-R1, QwQ-32B, R1-Distill-Qwen, and Phi-4-Reasoning-Plus show that FFS matches or surpasses strong baselin... | https://arxiv.org/abs/2505.18149v1 |
Baluja, D. Schuurmans, and X. Chen. Evolving deeper llm thinking. arXiv preprint arXiv:2501.09891 , 2025. [12] N. Levi. A simple model of inference scaling laws. arXiv preprint arXiv:2410.16377 , 2024. [13] D. Li, S. Cao, C. Cao, X. Li, S. Tan, K. Keutzer, J. Xing, J. E. Gonzalez, and I. Stoica. S*: Test time scaling f... | https://arxiv.org/abs/2505.18149v1 |
Harchaoui. From decoding to meta-generation: Inference-time algorithms for large language models. arXiv preprint arXiv:2406.16838 , 2024. [30] Y . Wu, Z. Sun, S. Li, S. Welleck, and Y . Yang. An empirical analysis of compute-optimal inference for problem-solving with language models. 2024. [31] Y . Xie, A. Goyal, W. Zh... | https://arxiv.org/abs/2505.18149v1 |
Lshould be larger than 1. Pr(C|S) =Pr(S|C)·Pr(C) Pr(S|C)·Pr(C) + Pr( S| ¬C)·Pr(¬C) Or, L=Pr(C|S) Pr(C)=Pr(S|C) Pr(S|C)·Pr(C) + Pr( S| ¬C)·Pr(¬C) =1 Pr(C) +Pr(S|¬C) Pr(S|C)·Pr(¬C) But we knowPr(S|¬C) Pr(S|C)is vanishingly small as correct traces are much more likely to be short than incorrect ones. Hence we have, L=1 Pr... | https://arxiv.org/abs/2505.18149v1 |
provide the Python implementation for parsing the final response from the reasoning traces for the AIME and GPQA datasets in Listings 1 and 2, respectively. 1DIGITS = ["1", "2", "3", "4", "5", "6", "7", "8", "9", "0"] 2 3import itertools 4import re 5 6def parse_output ( output ): 7 last = output . rfind ("\\ boxed {") ... | https://arxiv.org/abs/2505.18149v1 |
of order 8,8must divide p−1, sop≡1 mod 8 . So primes p≡1 mod 8 . But the problem says “the least prime p”. The primes congruent to 1 mod 8 start at17,97, etc. Wait, no, 17is1 mod 8 ? Let me check: 17divided by 8is2∗8 = 16 , so remainder 1. Yes, 17≡1 mod 8 . Then 97is12∗8 + 1 = 97 . But hold on, maybe there are smaller ... | https://arxiv.org/abs/2505.18149v1 |
= 1 ,64= 1296 ≡1296−99∗13 = 1296 −1287 = 9 , etc. So n4mod 13 is1,3,9. So−1 mod 13 is12. So no nwithn4≡12 mod 13 . So,p= 13 is out. Similarly, p= 17 . Let’s check if there is an n with n4≡ −1 mod 17 .−1 mod 17 is16. So,n4≡16 mod 17 . Let’s see. Let’s compute n4forn= 1to16. 14= 1 24= 16 . Oh, so 24= 16≡ −1 mod 17 . Son=... | https://arxiv.org/abs/2505.18149v1 |
positive k is 9. Therefore, n= 2 + 17 ∗9 = 2 + 153 = 155 . Therefore, m= 155 . But wait, let’s check if 1554+ 1is divisible by 172= 289 . But155 mod 17 :17∗9 = 153 , so155≡2 mod 17 . Then 24+ 1 = 17 , which is 0 mod 17 , as expected. Now, to check mod 289 . Let’s compute 1554+ 1 mod 289 . But calculating 1554is tedious... | https://arxiv.org/abs/2505.18149v1 |
Then, as before, divide both sides by 17:15k≡273/17 mod 17 .273divided by 17is 16.058... Wait, 17∗16 = 272 , so273 = 17 ∗16 + 1 . So 273 = 17 ∗16 + 1 . Therefore, 273/17 = 16+1 /17. So,255k≡273 mod 289 is equivalent to 15k≡16+1 /17 mod 17 . Wait, but dividing both sides by 17in the congruence 255k≡273 mod 289 , which i... | https://arxiv.org/abs/2505.18149v1 |
by 289 : 289 ∗5 = 1445 , so1444 = 1445 −1≡ −1 mod 289 . So1554= (1552)2≡(−1) mod 289 . Therefore, 1554+ 1≡ −1 + 1 = 0 mod 289 . Therefore, 1554+ 1 is divisible by 289. So my earlier assertion that 1554+ 1≡2 mod 289 was incorrect. Probably a miscalculation. Therefore, m= 155 is indeed the minimal solution. But wait, the... | https://arxiv.org/abs/2505.18149v1 |
+ 61846 = 2084846 .2085137 −2084846 = 291 .291 mod 289 = 2 . So not divisible. Alternatively, since Hensel’s lemma gives a unique solution, the minimal mis155. Therefore, the answer is 155. But let me check in the literature. I recall that 2is the smallest solution mod 17 , and lifting it gives 155. Also, since 17is th... | https://arxiv.org/abs/2505.18149v1 |
a prime. Let me check p= 2 first. Ifp= 2, then p2= 4. So we need n4+ 1≡0 mod 4 . Let’s check n= 1:1 + 1 = 2 ≡2 mod 4 . Not 0.n= 2:16 + 1 = 17 ≡1 mod 4 .n= 3:81 + 1 = 82 ≡2 mod 4 . So no nexists such that n4+ 1≡0 mod 4 . Therefore, p= 2is invalid. So pmust be 1 mod 8 . The primes congruent to 1 mod 8 are17,97, etc. Wait... | https://arxiv.org/abs/2505.18149v1 |
Let’s compute. 14= 1, 24= 16≡3,34= 81≡3,44= 256 ≡9,54= 625 ≡625−48∗13=625−624 = 1 , 64= 1296 ≡1296−99∗13 = 1296 −1287 = 9 ,74= 2401 ≡2401−184∗13 = 2401−2392 = 9 ,84= 4096 ≡4096−315∗13 = 4096 −4095 = 1 , etc. So possible residues are 1,3,9. So−1 mod 13 is12, which is not among them. Hence p= 13 is out. 20 Similarly, p= ... | https://arxiv.org/abs/2505.18149v1 |
term is 0 mod 289 . Fifth term: (17k)4= 174k4= 83521 k4≡0 mod 289 . So, combining all terms: (8 + 17 k)4+ 1≡50 + 1 + 136 kmod 289 ≡51 + 136 kmod 289 . We need this ≡0 mod 289 , so: 51 + 136 k≡0 mod 289 = ⇒136k≡ −51 mod 289 . Let me compute −51 mod 289 :289−51 = 238 . So136k≡238 mod 289 . We need to solve for k: 136k≡23... | https://arxiv.org/abs/2505.18149v1 |
mod 289 . But−51 mod 289 is238. So136k≡238 mod 289 . Asgcd(136 ,289) = 17 , which divides 238, so solutions exist. Dividing equation by 17: 8k≡14 mod 17 . Then inverse of 8 mod 17 is15, sok≡14∗15 = 210 ≡6 mod 17 . Sok= 6 + 17 t. So minimal k= 6. Then m= 8 + 17 ∗6 = 8 + 102 = 110 . Then why does 1104+ 1≡51 + 136 ∗6 = 51... | https://arxiv.org/abs/2505.18149v1 |
arXiv:2505.18152v2 [cs.CL] 26 May 2025 Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs Wafa Alghallabi1†Ritesh Thawkar1†Sara Ghaboura1†Ketan More1†Omkar Thawakar1† Hisham Cholakkal1Salman Khan1,2Rao Muhammad Anwer1,3 1Mohamed bin Zayed University of AI,2Australian National Univers... | https://arxiv.org/abs/2505.18152v2 |
✓ Poetic Device Annotation ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✓ Verse/Sentence-Level Annotation ✗ ✓ ✓ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✓ Temporal/Historical Context ✗ ✓ ✓ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✓ QA-Style Task Format ✗ ✗ ✗ ✗ ✓ ✓ ✓ ✗ ✗ ✗ ✗ ✓ Open-Source ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ Table 1: Comparison of key Arabic NLP datasets. Existing Arabic NLP resources ty... | https://arxiv.org/abs/2505.18152v2 |
poem-explanation pairs curated from 12 distinct historical poetic eras (see Figure 1), which can be broadly seen as spanning three major historical periods: pre-Islamic, classical, and con- temporary. It covers 14 poetic genres and includes a range of metrical forms, as detailed in Table 1. Each sample is manually veri... | https://arxiv.org/abs/2505.18152v2 |
struggle with the interpretive depth required by poetry. These findings highlight the need for culturally informed benchmarks that better reflect the depth and di- versity of Arabic. We release Fann or Flop as an open-source resource to support the development and evaluation of Arabic-capable language models. 2 The Fan... | https://arxiv.org/abs/2505.18152v2 |
: ﻓﺴKLي ﻓﺄُﻣّﻲ أرض ﻗﻮﻣﻚِ إﻧّi: ﻧﺪاءٌ ةﺮﻋﺎﺸﻠﻟ وأ) (ﺔﺛﺪﺤﺘﳌا ﻮﻋﺪﺗ ﮫﻴﻓ إN ) زfﺎرة أرض ﺔﻠﻴﺒﻗ ،ﺔﻋﻮﻃ ﻔﺼﺗو uﺎ ﺄﺑ¢nﺎ !ﺎﻷمّ ﻟﺎﺑg ﺔﺒﺴ ﻟu،ﺎ ﻣُﻌrLة ﻦﻋ ﺔﻗﻼﻋ ﻮﻗ f ﺔ وارﺗﺒﺎط ﻲﻔﻃﺎﻋ . أرى ﺣُﻘْﺒَﺔً ﺧَﻮْﻗَﺎءَ ﺟَﻤّﺎً ﻓُﺜُﻮﻗُuَﺎ: ﻒﺼﺗ ةﺮﻋﺎﺸﻟا ﺔﻘﻄﻨﻣ ﻦﻣ اﻷرض )ﺣُﻘْﺒَﺔ( ﺄﺑ¢nﺎ ﻌﺳاو ﺔ ﺔﺒﺼﺧو )ﺧَﻮْﻗَﺎءَ ﺟَﻤّﺎً(، وأنّ ﺛﻤﺎر8ﺎ ﻓو K L ة )ﻓُﺜُﻮﻗُuَﺎ(. ﺖ... | https://arxiv.org/abs/2505.18152v2 |
ﻦﻣو ﮫﻌﻣ ﻊﻣ أ8ﮫﻠ ،ﺮﻋﺎﺸﻟا ﻌﻤﺑ q أنﱠ ﺮﻋﺎﺸﻟا ﻻ ﺐﻏﺮﻳ اﻻرﺗﺒطﺎ وأ ﺔﻛرﺎﺸﳌا ﻌﻣuﻢ piء. ﻻ ﺗَﺠْﻤَﻌَﻦْ ﺷَ>ْﻠَuُﻢُ وَﺷَﻜِْ: ﻃﻠﺐٌ او »¸ٌ ﻦﻣ اW ﻢﻛﺎ «مﺪﻌ اW X ﻊﻤ ﺑGﮫﻨ و K ن ﳌﺎﻈﻟا K ،ن مﺪﻋو رﻂ ﺼﻣ K L ﻩ ﺼﻤﺑ KL8 ،ﻢ ﻓu ﻮ ﺾﻓﺮﻳ ﺗﻤﺎﻣﺎً ﻟاÁ ﮫﺑﺎﺸ وأ اﻻرﺗﺒﺎط Ën ﻢ….. :ﺮﻋﺎﺸﻟا ﻟَﺒﻴﺪُ ﺑﻦُ رَuﻴﻌَﺔَ :عﻮﻨﻟا قاﺮﻓ ﺰﺟﺮﻟا : ﺮﺤﺑ ﻳﺎ xَﺮِﻣﺎً وَأ... | https://arxiv.org/abs/2505.18152v2 |
This figure presents curated excerpts from Arabic poems spanning key historical eras, illustrating the evolution of language, themes, and stylistic expression. The Pre-Islamic sample reflects tribal valor and rhetorical precision; the Umayyad excerpt captures satire and social commentary; the Abbasid example highlights... | https://arxiv.org/abs/2505.18152v2 |
those with missing or ambiguous metadata, such as unknown poets or unspecified histori- cal eras, resulting in a curated dataset of 6,984 high-quality poems. -Unicode Normalization: All poems were standardized using Unicode normalization toaddress orthographic inconsistencies common in Arabic, including variations in d... | https://arxiv.org/abs/2505.18152v2 |
understanding. Model Pre-Islamic Transitional Early Islamic Umayyad Abbasid FatimidClosedGPT-4o-2024-08-06 (OpenAI, 2024) 0.6285 0.6304 0.6341 0.6285 0.6421 0.6398 GPT-4o-mini-2024-07-18 (OpenAI, 2024) 0.5980 0.6060 0.6134 0.5998 0.6125 0.6127 Gemini-2.5-Flash (AI, 2025b) 0.6245 0.6264 0.6286 0.6253 0.6326 0.6282 Gemin... | https://arxiv.org/abs/2505.18152v2 |
this approach provides a deeper measure of semantic consistency, capturing whether the gener- ated interpretation remains faithful to the intended meaning of the expert-authored reference, even when expressed using different lexical or syntactic forms. For LLM-as-Judge evaluation, we assess two key aspects: faithfulnes... | https://arxiv.org/abs/2505.18152v2 |
،كﻠﻣﻟا ﺎﮭﯾﻠﻋ رطﯾﺳﯾ ﻲﺗﻟا ثرﺎﺣﻟا رﯾﺛﺄﺗ ﺔﯾرارﻣﺗﺳﺎﺑ ﻲﺣوﯾ "دﻌﺑ" ﺔﻣﻠﻛ مادﺧﺗﺳا نأ ﺎﻣﻛ .ﺔﺑﯾﮭﻟاو .ﺔﯾﺧﯾرﺎﺗﻟا ﮫﺗﻧﺎﻛﻣ نﻣ ززﻌﯾ ﺎﻣﻣ ،ﮫﻠﯾﺣر دﻌﺑ ﻰﺗﺣ ﻣُﺟَﺎوَرَةً ﺑَﻧِﻲ ﺷَﻣَﺟَﻰ ﺑْنِ ﺟَرْمٍ ھَوَاﻧًﺎ ﻣَﺎ أُﺗِﯾﺢَ ﻣِنَ اﻟْﮭَوَانِ ةروﺎﺟﻣﻟا هذھ فﺻﯾو ،مرﺟ نﺑ ﻰﺟﻣﺷ ﻲﻧﺑ ةروﺎﺟﻣ ﻰﻟإ رﻋﺎﺷﻟا رﯾﺷﯾ رﻋﺎﺷﻟا مدﺧﺗﺳﯾ .لﺋﺎﺑﻘﻟا نﯾﺑ عارﺻﻟاو رﺗوﺗﻟا سﻛﻌﯾ ﺎﻣﻣ ،نا... | https://arxiv.org/abs/2505.18152v2 |
نﻋ رﯾﺑﻌﺗﻠﻟ ﺔﯾﻧﻛﻣ ةرﺎﻌﺗﺳﺎﻛ "نﺎﻧﺣﻟا اذ كﻧﺎﻧﺣ" نﯾﻣدﺧﺗﺳﻣ ﻲﺗﺗﺣول إﻟﻰ ﺳﻼح ﺿده. اﻟﺗﺷﺑﯾﮫ اﻟﺿﻣﻧﻲ ﺑﯾن اﻟﺣﻧﺎن واﻟﻘوة ﯾُﺑرز ﺗﻧﺎﻗﺿًﺎ دراﻣﯾًﺎ، ﺑﯾﻧﻣﺎ اﻟطﺑﺎق ﺑﯾن "ﻣﻧﻊ" و"ﺣﻧﺎن" ﯾُﺑرز ﺗﻧﺎﻗض اﻟﻘوة واﻟﺿﻌف ،ﻣﻣﺎ ﯾُظﮭر ﺗﻔوق اﻟﻘﺑﯾﻠﺔ ﻋﻠﻰ اﻟﻣﻠك اﻟﺳﺎﺑق.Qwen3أَﺑَﻌْدَ اﻟْﺣﺎرِثِ اﻟْﻣَﻠِكِ اﺑْنِ ﻋَﻣْرٍو ﻟَﮫُ ﻣُﻠْكُ اﻟْﻌِرَاقِ إِﻟَﻰ ﻋُﻣَﺎنِ ﺔﻛﻠﻣﻣ كﻠﺗ... | https://arxiv.org/abs/2505.18152v2 |
convey its intended meaning. Arabic poetry. Our analysis highlights the impor- tance of domain-specific evaluation for literary and cultural tasks. It also underscores the need for building or fine-tuning models that are more sen- sitive to classical Arabic forms. The gap between fluency and interpretive depth in some ... | https://arxiv.org/abs/2505.18152v2 |
dataset to include more diverse annotations, as well as dialectal and regional poetic forms, re- mains a key area for future work.On the societal front, this benchmark contributes to the preservation and computational accessibility of Arabic literary heritage by positioning poetry as a meaningful testbed for language u... | https://arxiv.org/abs/2505.18152v2 |
conference on artificial intelligence , volume 34, pages 7432–7439. Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alexan- der Erdmann, et al. 2018. The madar arabic dialect corpus and lexicon. In Proceedings of the eleventh inter... | https://arxiv.org/abs/2505.18152v2 |
oriented learning of named entities in arabic wikipedia. In Proceedings of the 13th Conference of the European Chapter of the Association for Compu- tational Linguistics , pages 162–173. Hussein Mozannar, Karl El Hajal, Elie Maamary, and Hazem Hajj. 2019. Neural arabic question answering. arXiv preprint arXiv:1906.0539... | https://arxiv.org/abs/2505.18152v2 |
auto- diacritization systems. Data in brief , 11:147. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Eval- uating text generation with bert. arXiv preprint arXiv:1904.09675 . Cheng Zhao, Bin Wang, and Zhen Wang. 2024. Understanding literary texts by llms: A case study of a... | https://arxiv.org/abs/2505.18152v2 |
identification, and poet recog- nition, along with descriptive metadata. Despite its contributions to computational poetics, Ashaar lacks verse-level annotation, rhetorical device mod- eling, question-answer style interpretation, and his- torical contextualization, limiting its ability to eval- uate deeper poetic reaso... | https://arxiv.org/abs/2505.18152v2 |
Hajar 35 al-Samaw’al 12 al-Sulayk ibn al-Sulaka 7 Imru’ al-Qais ibn Hujr 34 Zuhayr ibn Abi Sulma 48 Salama ibn Jandal 14 Tarfah ibn al-Abd 26 Urwah ibn al-Ward al-Absi 31 Ubayd ibn al-Abras 40 Amr ibn Qami’a 21 Amr ibn Kulthum 24 Antarah ibn Shaddad 82 Total 374 Table 5: Poem counts for major poets from the Pre-Islamic... | https://arxiv.org/abs/2505.18152v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.