text string | source string |
|---|---|
LILI YU, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. 2023. LIMA: Less is more for alignment. In Advances in Neural Information Processing Systems , volume 36, pages 55006–55021. Curran Associates, Inc. 12 A Pretrained or Backbone Choice We experimented with several pretrained or base model ch... | https://arxiv.org/abs/2505.16967v1 |
x 4 3 ∼24 hours 0.668 0.327 0.304 0.608 Table 9: Model configuration, training settings, and retrieval results (nDCG@10) for backbone models fine-tuned on the BGE-training dataset (1.6M training pairs) and evaluated on four datasets from the BEIR benchmark. The models are sorted according to parameter size; The best sc... | https://arxiv.org/abs/2505.16967v1 |
dataset at a time and fine-tuning the rest. Improved denotes E5 (base) with a nDCG@10 better than +1point, Reduced with a nDCG@10 worse than −1point, and NoChange within the ±1point range, compared to part (b) E5 (base) fine-tuned on ALL Training Pairs. Each row in part (c) is fine-tuned on all but one left-out dataset... | https://arxiv.org/abs/2505.16967v1 |
<worse> Relevant but not preferred over ground truth: [Doc (1) . . . ] </worse> </verdict> ———– <question> {question }</question> <ground_truth> {ground _truth }</ground_truth> <documents> {documents }</documents> Figure 6: Prompt used in RLHN with GPT-4o-mini and GPT-4o for relabeling hard negatives for all BGE traini... | https://arxiv.org/abs/2505.16967v1 |
arXiv:2505.16968v2 [cs.AR] 25 May 2025 CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark Ahmed Heakl1Sarim Hashmi†1Gustavo Bertolo Stahl†1Seung Hun Eddie Han1 Salman Khan1,2Abdulrahman Mahmoud1∗ 1MBZUAI2Australian National University /githubhttps://github.com/GustavoStahl/CASS ὑ7https://huggingface.co/... | https://arxiv.org/abs/2505.16968v2 |
focusing on correctness and alignment. While not optimization-aware yet, it paves the way for future systems that preserve and adapt performance-critical patterns across GPU backends. To address the lack of cross-architecture GPU translation datasets, we introduce CASS (CUDA–AMD ASsembly and Source Mapping), a large-sc... | https://arxiv.org/abs/2505.16968v2 |
Rodinia SHOC Poly Babel Ours Characteristics NVIDIA[19] Bench[20] [21] Bench[22] Stream[23] CUDA (source) ✓ ✓ ✓ ✓ ✓ ✓ SASS (assembly) ✗ ✗ ✗ ✗ ✗ ✓ RDNA3 (assembly) ✗ ✗ ✗ ✗ ✗ ✓ OpenCL (source) ✗ ✓ ✓ ✓ ✓ ✓ 2 Related Works In this section, we describe prior work in GPU translation efforts (§2.1), assembly-level transpilati... | https://arxiv.org/abs/2505.16968v2 |
AMD code and assem- bly. PolyBench [ 22] evaluates compilers with CUDA/OpenCL kernels, yet lacks assembly-level or AMD support. BabelStream [ 23] benchmarks HIP/CUDA/OpenCL memory bandwidth but excludes assembly and domain diversity. Hetero-Mark [ 26] targets CPU–GPU workloads where GPU code is minimal. The Stack [ 11,... | https://arxiv.org/abs/2505.16968v2 |
with a {size}X{size} grid. Optimize for {optimization}. To fill these templates, we prepared predefined lists of variable values. For instance, {size} was instantiated with values such as 32, 64, and 128, while {optimization} was sampled from options like "memory bandwidth", "register usage", and "multi-GPU scaling". T... | https://arxiv.org/abs/2505.16968v2 |
[ 30] and convert them into PTX, after which the CUDA stack was used to compile them down to assemblies. On the AMD stack, clang was used to directly transpile the OpenCL files into device assemblies whilst forcing it to emit intermediate LLVM during this process [17]. In total, these pipelines produced 70k aligned ass... | https://arxiv.org/abs/2505.16968v2 |
domains 0% in math, data structures, and graph tasks, 25–50% in linear algebra and memory operations, and up to 100% in physics simulations—highlighting the challenge of preserving low-level semantics. Despite this, the translated code closely matches the original in execution: memory usage deviates by less than ±0.3%,... | https://arxiv.org/abs/2505.16968v2 |
the 16K-token context window of the LLM, we normalized CUDA assembly code by removing redundant whitespace and comments, which reduced token count by roughly 15%. No preprocessing was applied to HIP assembly code due to its sensitivity to whitespace changes. We fine-tuned the Qwen2.5-Coder [32] models at 1.5B, 3B and 7... | https://arxiv.org/abs/2505.16968v2 |
role in learning low-level patterns. OpenCL adds +2.5%, providing complementary coverage, while RoPE extrapolation pushes accuracy to 37.5% by extending context capacity. 7 Limitations and Future Work Despite achieving state-of-the-art assembly transpilation, current performance is inadequate for production due to limi... | https://arxiv.org/abs/2505.16968v2 |
2025-05-14. [14] AMD ROCm Documentation. HIP Porting Guide , 2024. Accessed: 2025-01-29. [15] Jun Chen, Xule Zhou, and Hyesoon Kim. Cupbop-amd: Extending cuda to amd platforms. In Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis , pages 109... | https://arxiv.org/abs/2505.16968v2 |
translation , pages 392–395, 2015. [32] Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jia- jun Zhang, Bowen Yu, Keming Lu, et al. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 , 2024. [33] Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. Deepspeed... | https://arxiv.org/abs/2505.16968v2 |
output than HIP for equivalent source sizes. 13 Figure 8: Opcode Category Distribution by Dataset and Code Type. Stacked bar chart showing the distribution of assembly instructions across 10 opcode categories for device and host code in the Synthetic, Stackv2, and OpenCL subsets. Each bar represents a (dataset, code ty... | https://arxiv.org/abs/2505.16968v2 |
scales. A.4.2 Code efficiency As shown figure 5, assembly accuracy is inconsistent, 0% in Math, Data Structures, and Graph, 25–50% in linear algebra and memory operations. This reflects the challenge of low-level semantic preservation. Only physics simulation achieves 100%, likely due to simpler or repetitive control f... | https://arxiv.org/abs/2505.16968v2 |
{radius} 1, 5, 13 {graph_format} adjacency matrix, CSR, edge list {md_algorithm} Verlet integration, leapfrog, Runge-Kutta {linear_solver} conjugate gradient, Jacobi, multigrid {numerical_method} finite difference, spectral, Crank-Nicolson {factorization_method} SVD, LU, eigenvalue decomposition {conv_layer_count} 2, 6... | https://arxiv.org/abs/2505.16968v2 |
3. Write a CUDA implementation for sparse convolution with {size}x{size} filter on sparse input. Focus on {optimization}. 4. Create a CUDA implementation for sparse matrix-matrix multiplication in { sparse_format} format. Focus on {optimization}. 5. Generate a CUDA kernel for sparse matrix-vector multiplication where t... | https://arxiv.org/abs/2505.16968v2 |
scenarios where clarity and consistency matter. In contrast, Claude, Qwen-Coder, and GPT4o unnecessarily altered the string to say HIP, despite the output still originating from a CUDA kernel. This substitution introduces a semantic error, as the original string refers to CUDA, not HIP, and should remain unchanged. CAS... | https://arxiv.org/abs/2505.16968v2 |
arXiv:2505.16972v1 [cs.CL] 22 May 2025From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition Tianduo Wang♡*,Lu Xu♢,Wei Lu♡,Shanbo Cheng♢† ♡StatNLP Research Group, Singapore University of Technology and Design ♢ByteDance Seed {tianduo_wang,luwei}@sutd.edu.sg ,{xu.lu1,chengshanbo}@byteda... | https://arxiv.org/abs/2505.16972v1 |
Back-Translation (see Figure 1), a scalable method that build large- scale synthetic transcribed speech from text cor- pora with TTS models. Our results demonstrate that synthetic data, generated by TTS models trained on just tens of hours of labeled audio, can effectively expand small human-labeled datasets to tens of... | https://arxiv.org/abs/2505.16972v1 |
of high-quality speech for previously unseen speak- ers without additional fine-tuning. These models typically contain the following components: •Audio Tokenizer : Encodes raw acoustic inputs (e.g., mel-spectrograms) into discrete audio to- kens, forming the basis for synthesis. •Speaker Embeddings : Contain speaker-sp... | https://arxiv.org/abs/2505.16972v1 |
we propose a novel metric called Normalized Intel- ligibility , leveraging ASR performance on natu- ral speech as a reference baseline. We use the Fleurs dataset (Conneau et al., 2022), which pro- vides high-quality audio-transcript pairs across 102 languages, and Whisper-large-v3 as our judge ASR system. By synthesizi... | https://arxiv.org/abs/2505.16972v1 |
(769M), and Large (1.5B). Fur- ther training details are provided in Appendix E. 4.2 Zero-shot TTS Models We employ two state-of-the-art zero-shot TTS mod- els in our experiments: XTTS (Casanova et al., 2024) and ChatTTS (2noise, 2024). XTTS sup- ports 16 languages, covering a range of language families and resource le... | https://arxiv.org/abs/2505.16972v1 |
3: Comparison of dataset sizes across seven languages (log-scale y-axis). Languages are catego- rized by resource availability in the Whisper dataset: (a) high-resource, (b) mid and low-resource groups. we analyze the relationship between TTS quality and ASR performance using our fine-tuned TTS model (Section 5.3), and... | https://arxiv.org/abs/2505.16972v1 |
real data with Speech BT significantly enhances both in-domain (6.6% for Whisper-medium, 6.3% for Whisper-large) and out- of-domain performance (4.1% and 3.3%, respec- tively). This clearly demonstrates that our synthetic data not only improves model robustness within- domain but also enhances generalization capabili- ... | https://arxiv.org/abs/2505.16972v1 |
importance of achieving a minimum TTS quality level for effec- tive ASR data augmentation. Additionally, the vol- ume of TTS training data significantly influences the ability to surpass this intelligibility threshold. Models trained on larger datasets generally achieve higher intelligibility scores and yield greater A... | https://arxiv.org/abs/2505.16972v1 |
Low High Mid Low High Mid SeamlessM4T-medium 1.2B 13.3 12.8 24.4 10.7 20.0 12.6 8.0 13.0 Whisper-large-v2 1.5B 11.4 8.1 19.9 9.8 19.5 16.3 6.3 11.5 Whisper-large-v3 1.5B 10.1 5.9 15.6 12.6 28.6 14.4 5.3 10.2 + Real-only (15K Hrs) - 8.6 4.9 12.5 7.9 17.1 10.6 5.0 9.4 + Speech-BT (500K Hrs) - 7.8 4.3 8.3 7.6 16.2 8.0 4.4... | https://arxiv.org/abs/2505.16972v1 |
quality to significantly improve ASR perfor- mance. The large-scale implementation across ten languages with 500,000 hours of synthetic speech yielded an average 30% reduction in Whisper-large- v3’s transcription error rates, confirming the effec- tiveness and scalability of our approach. Speech Back-Translation challe... | https://arxiv.org/abs/2505.16972v1 |
ArXiv , 2304.08466. Matthew Baas and Herman Kamper. 2021. V oice con- version can improve asr in very low-resource settings. InProceedings of Interspeech . Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Miguel Pino, Alexei Bae... | https://arxiv.org/abs/2505.16972v1 |
Auli, and David Grangier. 2018. Understanding back-translation at scale. In Proceedings of EMNLP . Lijie Fan, Kaifeng Chen, Dilip Krishnan, Dina Katabi, Phillip Isola, and Yonglong Tian. 2023. Scaling laws of synthetic images for model training . . . for now. InProceedings of CVPR . Heting Gao, Kaizhi Qian, Junrui Ni, ... | https://arxiv.org/abs/2505.16972v1 |
Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, et al. 2024. Less is more: Accurate speech recognition & translation without web-scale data. ArXiv , 2406.19674. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brock- man, Christine McLeavey, and Ilya Sutskever. 2022. Robust speech recognition via large-... | https://arxiv.org/abs/2505.16972v1 |
Liu Yang, Xilin Luo, Xue Gang Wu, Lunan Liu, Wenjun Cheng, et al. 2023. Skywork: A more open bilingual foundation model. ArXiv , 2310.19341. Guanrou Yang, Fan Yu, Ziyang Ma, Zhihao Du, Zhifu Gao, Shiliang Zhang, and Xie Chen. 2024. Enhanc- ing low-resource asr through versatile tts: Bridging the data gap. ArXiv , 2410.... | https://arxiv.org/abs/2505.16972v1 |
CV16 en zh2345678WER/CER (%) 4.07.6 4.47.1(b) Out-of-Domain: FleursFigure 7: Comparison of Whisper-medium ASR perfor- mance on in-domain (CV16) and out-of-domain (Fleurs) test sets, as well as TTS quality, when training with syn- thetic Chinese and English speech generated by XTTS and ChatTTS. (0.96 vs 0.74) while Chat... | https://arxiv.org/abs/2505.16972v1 |
guages extracted from European Parliament pro- ceedings. We utilize 8th version of the dataset. SkyPile (Wei et al., 2023) SkyPile is a large- scale Chinese dataset containing approximately 150 billion tokens, curated specifically for pre- training large language models. The corpus is compiled from diverse Chinese web ... | https://arxiv.org/abs/2505.16972v1 |
reduc- ing overfitting. Subsequent work has explored variants of back-translation such as iterative back- translation, filtering synthetic data by quality, and domain adaptation strategies (Edunov et al., 2018; Hoang et al., 2018). In addition, dual learning frameworks have incorporated back-translation and forward-tra... | https://arxiv.org/abs/2505.16972v1 |
+ Speech BT (500K Hrs) - 5.6 8.4 9.0 7.4 12.5 19.8 7.6 8.3 Table 9: Performance comparison across languages on V oxpopuli. Model SizeHigh Mid Low en fr de es zh nl it cs hu vi SeamlessM4T-medium 1.2B 11.3 14.5 12.1 9.8 18.7 15.2 10.4 14.4 34.8 24.1 Canary 1.0B 8.6 6.9 5.1 4.4 - - - - - - Whisper-large 1.5B 12.2 15.0 8.... | https://arxiv.org/abs/2505.16972v1 |
arXiv:2505.16973v2 [cs.CL] 23 May 2025/searc/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀t/b♀tVERIFASTSCORE : Speeding up long-form factuality evaluation Rishanth Rajendhran1Amir Zadeh2Matthew Sarte2Chuan Li2Mohit Iyyer1 1University of Maryland 2Lambda Labs {rishanth, miyyer}@umd.edu Abstract Metrics ... | https://arxiv.org/abs/2505.16973v2 |
Pearson correlation of only 0.33 with VERISCORE despite high API costs. Despite these challenges, VERIFASTSCORE matches the quality of VERISCORE closely while offering substantial improvements in both cost and runtime efficiency: it achieves a Pearson correlation of 0.80(Pearson r, p<0.001) with VERISCORE ’s scores, a ... | https://arxiv.org/abs/2505.16973v2 |
several calls to LLMs to complete for a single response. These limitations motivate our design and development of VERIFASTSCORE , which combines all steps in the existing factuality evaluation pipeline into a single model call. To enable such a fast evaluation, we generate synthetic data from VERISCORE and use it to fi... | https://arxiv.org/abs/2505.16973v2 |
a query to retrieve evidence via Google Search. Finally, a claim veri- fication model checks the factuality of each claim against the retrieved evidence. While this careful decomposition and step-wise verification ensures precision, it incurs significant computational cost. On average, a single response of 14 sentences... | https://arxiv.org/abs/2505.16973v2 |
(1,|C| K) where Kis the median number of verifiable claims across model responses. We compute F1@K(r): F1@K(r) =(2P(r)RK(r) P(r)+RK(r)ifS(r)>0 0 ifS(r) = 0 The final score for a model Macross a dataset Xis: VERIFASTSCORE =1 |X|X x∈XF1@K(Mx)(1) 2.4 Generating Synthetic Training Data for VERIFASTSCORE Data Sources and Mo... | https://arxiv.org/abs/2505.16973v2 |
71.6 15.5 12.3 0.87 sentence-levelGPT-4o few-shot ICL 0.38 0.34 19.3 8.2 71.2 0.33 VERIFASTSCORE 0.83 0.86 66 17.6 15 0.80 Table 3: Performance metrics across test splits: VERIFASTSCORE produces claims and verification labels that are largely consistent with VERISCORE , achieving a strong corelation of 0.80 even with s... | https://arxiv.org/abs/2505.16973v2 |
Metrics Since we motivate VERIFASTSCORE as a speedy replacement to the multi-stage pipeline of VERISCORE , we want its outputs to be closely aligned with outputs from VERISCORE . We evalu- ate V ERIFASTSCORE using three main metrics: •Claim Precision: Computed as the proportion of claims produced by VERIFASTSCORE that ... | https://arxiv.org/abs/2505.16973v2 |
random subset of 100 prompts from the test split of Tulu3-Personas data. The rankings produced by both models are fairly consistent with each other despite some differences in order. There is a clear separation between open-weight and closed- weight models. 6 Example (truncated) Remarks Response . . . The “chimney” and... | https://arxiv.org/abs/2505.16973v2 |
about 29% of the instances. These results underscore the complexi- ties involved in simultaneous claim extraction and verification.3.2 Speedup Average time spent (s) Evidence retrievalModeling VERISCORE 21.4 83.0 VERIFASTSCORE 13.5 9.5 Speedup 1.9x 9.9x Table 5: Execution time: VERIFASTSCORE spends sig- nificantly less... | https://arxiv.org/abs/2505.16973v2 |
decomposition consistency. Chen et al. (2023) and Yue et al. (2024) report failures tied to vague or anaphoric claims. Hu et al. (2025) cata- log common decomposition errors and tradeoffs. VERISCORE explicitly avoids unverifiable content like opinions or suggestions (Song et al., 2024). End-to-End and Lightweight Appro... | https://arxiv.org/abs/2505.16973v2 |
Language and configuration limitations. Our experiments focus primarily on English-languageoutputs. Although some non-English generations were present, we did not conduct language-specific analysis. Additionally, we only minimally modi- fied prompts from VERISCORE and did not exhaus- tively tune training configurations... | https://arxiv.org/abs/2505.16973v2 |
Quanyu Long, and Wenya Wang. 2025. Decomposition dilemmas: Does claim decompo- sition boost or burden fact-checking performance? Preprint , arXiv:2411.02400. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Men- sch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guil- laume... | https://arxiv.org/abs/2505.16973v2 |
Qiu. 2025. Qwen2.5 technical report. Preprint , arXiv:2412.15115. Alessandro Scirè, Andrei Stefan Bejgu, Simone Tedeschi, Karim Ghonim, Federico Martelli, and Roberto Navigli. 2025. Truth or mirage? to- wards end-to-end factuality evaluation with llm-oasis. Preprint , arXiv:2411.19655. 10 Yixiao Song, Yekyung Kim, and ... | https://arxiv.org/abs/2505.16973v2 |
Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuancheng Ren, Xuejing Liu, Yang Fan, Yang Yao, Yichang Zhang, Yu Wan, Yunfei Chu, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Z... | https://arxiv.org/abs/2505.16973v2 |
To avoid overfitting, we added a dropout layer in both of these configurations and ablated by freezing the language model parameters. We also experi- mented with a multi-task learning setup with losses computed with both the scoring head output and the decomposition and verification outputs from the language modeling h... | https://arxiv.org/abs/2505.16973v2 |
is likely due to the sentence-level retrieval strategy used by VERIFASTSCORE , which may issue underspecified queries and produce loosely related results. These limitations in evidence quality can contribute both to omission in extraction and errors in verification. A.4 Automatic Filtering of Tulu3 prompts 13 Table 7: ... | https://arxiv.org/abs/2505.16973v2 |
the Florence city hall. Text: After the success of the David in 1504, Michelangelo’s work consisted almost entirely of vast projects. He was attracted to these ambitious tasks while at the same time rejecting the use of assistants, so that most of these projects were impractical and remained unfinished. In 1504 he agre... | https://arxiv.org/abs/2505.16973v2 |
not provide the groundwork for abstract concepts like science and algebra. Facts: •Stuyvesant High School is in New York City. •Stuyvesant High School is an elite high school. •Stuyvesant High School is a public school. •In 1972, St. Joseph’s catholic school education did not provide the groundwork for abstract concept... | https://arxiv.org/abs/2505.16973v2 |
judgment of fact 1> <fact 2>: <your judgment of fact 2> . . . <fact n>: <your judgment of fact n> If no verifiable claim can be extracted, simply output "No verifiable claim." ### Response: Historical Context and Significance: In the summer of 1215, a pivotal moment in the course of Western political and legal history ... | https://arxiv.org/abs/2505.16973v2 |
of Brig. Gen. John S. Brown, ... hours This course examines the causes and consequences of globalization. Issues are examined from a changing historical context of economy, politics, and ... ... along the south bank of the Thames River, in a meadow called Runnymede. King John affixed his seal to the Magna Carta on June... | https://arxiv.org/abs/2505.16973v2 |
that step was neither the first nor yet the final one.2. In ... The Magna Carta, Latin for “Great Charter,” is one of the most famous documents in history. It was originally issued in 1215 during the reign of ... A law made by the king in one national assembly might be repealed by the king in another; whereas the Great... | https://arxiv.org/abs/2505.16973v2 |
handle its business without interference from the throne; that no free man could be imprisoned or outlawed except by ... One of the most important, and often quoted, provisions stated that "no freeman shall be seized, imprisoned, dispossessed, outlawed, or exiled, or in any way ... The Federalist # 78 states further th... | https://arxiv.org/abs/2505.16973v2 |
has been repealed; however, four clauses of the original charter are enshrined in the 1297 ... On the back of this charter issued in the name of King Æthelbald of Mercia in 736, it is still possible to see the impressions from where the document was ... The king and the rebel barons negotiated a peace settlement in Jun... | https://arxiv.org/abs/2505.16973v2 |
the world. D. The Bill of Rights to the U.S. Constitution ... In 1215, when King John confirmed Magna Carta with his seal, he was acknowledging the now firmly embedded concept that no man–not even the king ... As we celebrate 800 years of Magna Carta, it’s timely to reflect on the bloodshed and tyranny behind its creat... | https://arxiv.org/abs/2505.16973v2 |
The Magna Carta granted trial by jury.: Supported The Magna Carta was incepted more than eight centuries ago.: Unsupported The drafting of the Magna Carta took place in the summer of 1215.: Unsupported The Magna Carta was drafted in the summer of 1215.: Unsupported The Magna Carta serves as a symbol of liberty.: Suppor... | https://arxiv.org/abs/2505.16973v2 |
how many claims produced by VERISCORE but not by VERIFASTSCORE .Correlation b/w factuality scores is the Pearson’s correlation between factuality scores computed by VERIFASTSCORE andVERISCORE for model responses. Data Source, Evidence GranularityModel Precision ↑Recall ↑Claim Accuracy (%) Correlation b/w factuality sco... | https://arxiv.org/abs/2505.16973v2 |
1. Colleen Hoover’s Without Merit book is a work by Colleen Hoover. 2. Several titles by Colleen Hoover have become New York Times bestsellers. 3. Colleen Hoover’s Heart Bones book is a work by Colleen Hoover. 4. Colleen Hoover’s Slammed series includes 3 books. 5. Colleen Hoover has published 24 books as of February 2... | https://arxiv.org/abs/2505.16973v2 |
SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development Yaxin Du1∗, Yuzhu Cai2∗, Yifan Zhou3, Cheng Wang1, Yu Qian1, Xianghe Pang1, Qian Liu4,Yue Hu5, Siheng Chen1 1Shanghai Jiao Tong University,2Beijing University of Aeronautics and Astronautics, 3Soochow University,4Tiktok,5University of Michi... | https://arxiv.org/abs/2505.16975v1 |
is formally defined as feature-driven development (FDD) [ 5,6], which consists of 40% coding tasks of all development efforts [ 7,8]. FDD involves the end-to-end creation of new features, from interpreting requirements in large, existing codebases to generating functionally correct and integrated code (see Figure 1). F... | https://arxiv.org/abs/2505.16975v1 |
the proficiency and deficiencies of various coding systems (chatbot LLMs, reasoning LLMs, and MAS) on complex FDD tasks. •We demonstrate SWE-Dev enabling and validating diverse training paradigms (SFT, RL, and MAS training), establishing its utility for advancing training-based adaptation. 2 Table 1: Comparison of SWE-... | https://arxiv.org/abs/2505.16975v1 |
approaches largely focused on function-level tasks, limiting their applicability to more complex development scenarios. To address this, SWE-Gym[ 32] explores extending training to repository-scale tasks using multi-agent systems. However, due to the lack of an executable training set in SWE-Bench, SWE-Gym resorts to c... | https://arxiv.org/abs/2505.16975v1 |
all repositories are suitable: many lack usable tests or need sophisticated installation. Therefore, we applied a strict filtering process focused on test suite executability. Repositories were retained only if they met two criteria: (1) they include an identifiable test suite (e.g., using pytest orunittest ), and (2) ... | https://arxiv.org/abs/2505.16975v1 |
leaving a functional gap to fill. (2) Project Requirement Document (PRD) generation: We construct the feature description in PRD by using GPT-4o to synthesize a high-level module description from the test file and augmenting the masked function’s docstring with implementation-level details. These two elements are combi... | https://arxiv.org/abs/2505.16975v1 |
Full details of the evaluated methods are provided in Appendix F.1. 4.1.1 Single LLM Inference SWE-Dev presents substantial challenges for current LLMs, revealing a clear gap between existing coding capabilities and real-world software engineering demands. Figure 4 reports Pass@3 performance of chatbot and reasoning LL... | https://arxiv.org/abs/2505.16975v1 |
driven by GPT-4o-mini. Details of MAS are given in AppendixF.1. Key observations are: MAS generally outperforms single-agent baselines on complex tasks. While the single-agent approach achieves only 11.09% Pass@1 on hard tasks, Self Refine[ 34] and EvoMAC[ 18] improve performance to 20.03% and 13.60%, respectively. The... | https://arxiv.org/abs/2505.16975v1 |
of training using Qwen2.5-7b-instruct. In this experiment, we measured model performance across varying amounts of fine-tuning data, specifically tracking changes in Pass@1 for both easy and hard task. As shown in the figure, performance improves steadily as the amount of fine-tuning data increases, with larger improve... | https://arxiv.org/abs/2505.16975v1 |
training process of MAS on this dataset. As depicted in Fig. 7, the ground truth test case supervision in SWE-Dev enables EvoMAC [ 18] to improve its performance across multiple rounds of reasoning. This iterative refinement process motivates us to explore EvoMAC as the MAS for training in SWE-Dev. We apply rejection s... | https://arxiv.org/abs/2505.16975v1 |
GPT-4o. As Fig 8b shows, Pass@3 best reflects capability scaling, separating models by size and quality. In contrast, EM, ES, and CodeBLEU show minimal variance, failing to distinguish models. This demonstrates that SWE-Dev’s test-case- based evaluation provides a more robust and realistic signal of model performance, ... | https://arxiv.org/abs/2505.16975v1 |
May 10, 2025. This guide discusses FDD principles including planning by feature and aligning with business requirements, which are conducive to automated assessment via acceptance criteria. [9]Lily Kazerouni, April Mitchell, John Smith, and Emily Johnson. Large language models for software engineering: A systematic lit... | https://arxiv.org/abs/2505.16975v1 |
Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al. Competition-level code generation with alphacode. Science , 378(6624):1092–1097, 2022. [24] Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang,... | https://arxiv.org/abs/2505.16975v1 |
multi-agent debate, 2024. 12 [38] Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors, 2023.... | https://arxiv.org/abs/2505.16975v1 |
Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tianyi Tang, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, and Zihan Qiu. Q... | https://arxiv.org/abs/2505.16975v1 |
Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. Metagpt: Meta programming for a multi-agent collaborative framework, 2024. [62] Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, and Aviral Kumar. Archer: Training language model agents via hierarchical multi-turn rl, 2024. [63] Charlie S... | https://arxiv.org/abs/2505.16975v1 |
within the benchmark. src_dir Relative directory path where the source code files for the project or task are located. test_dir Relative directory path where the test code files for the project or task are located. test_file Relative path of the unit test file used for executing tests. GT_file_code Ground Truth source ... | https://arxiv.org/abs/2505.16975v1 |
and HumanEval (Pass@1 and Pass@3). ModelSWE-Dev pass@1 SWE-Dev pass@3 ComplexCodeEval CodeBLEUHumanEval pass@1HumanEval pass@3 Easy Hard Easy Hard Chatbot Qwen2.5-1.5B-Instruct 8.05% 1.23% 10.76% 2.22% 29.72% 57.20% 69.76% Qwen2.5-3B-Instruct 15.93% 5.27% 21.99% 7.47% 12.27% 62.68% 75.00% Qwen2.5-7B-Instruct 25.74% 6.6... | https://arxiv.org/abs/2505.16975v1 |
C.1 Analysis of PRD Quality Our Project Requirement Descriptions (PRDs) are primarily derived from the original docstrings found within the repository source code. To enhance the quality and utility of these PRDs, we employed GPT-4o to refine and improve the original docstrings. To objectively assess this improvement, ... | https://arxiv.org/abs/2505.16975v1 |
into five types: Incomplete, Logic, Syntax, Parameter, and Others, see error classification prompt in Figure 21. Across both agent types, the most prevalent error is the Incomplete Error, where models fail to implement PRD-required functions—indicating persistent challenges in task decomposition and execution coverage.... | https://arxiv.org/abs/2505.16975v1 |
,test_year , and test_ordinal_num . Each test function serves as a root for its own call path, triggering downstream functions like Num2Word_AZ.to_cardinal and Num2Word_AZ.int_to_word . This tree structure reveals the multi-level and cross-functional logic activated during test execution, illustrating how test files co... | https://arxiv.org/abs/2505.16975v1 |
a learning rate of 6×10−4and a batch size of 32 sequences per gradient step, for up to 4 epochs. Checkpoints are saved every 50 steps, and the best model is selected based on validation loss over a held-out set of 100 examples. Fine-tuning is initialized from Qwen2.5- 7B-Instruct and completed within 20 hours using 8 N... | https://arxiv.org/abs/2505.16975v1 |
sampling—a method widely adopted in reinforcement learning and language model fine-tuning [ 62,63]. The detailed procedure is as follows: 1.Iterative Reasoning with EvoMAC : For each training instance, EvoMAC executes multiple rounds of reasoning. In each iteration, the generated code from the Coder is tested against t... | https://arxiv.org/abs/2505.16975v1 |
Coding Agent Prompt You are Programmer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer. You can write/create computer software or applications by providing a specific programming language to the computer. You have extensive computin... | https://arxiv.org/abs/2505.16975v1 |
"Observed abnormal behavior (in Chinese)", "RootCause": "Attribution analysis combining PRD and code (in Chinese)", "ErrorMechanism": "Technical explanation of how the error occurs ( in Chinese)" } } } Below is the data provided to you: PRD: {prd} Generated Code: {results} Error Message: {input_text} Please ensure your... | https://arxiv.org/abs/2505.16975v1 |
API communication, and network protocols. Criteria: Enables browser control, HTTP requests, network operations, or web server handling. 2. Data Processing & Integration Packages that extract, parse, or convert structured/unstructured data formats. Criteria: Handles parsing or converting text, JSON, YAML, XML, or dates.... | https://arxiv.org/abs/2505.16975v1 |
arXiv:2505.16983v1 [cs.CL] 22 May 2025LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding Junlong Tong1,2, Jinlan Fu3, Zixuan Lin4, Yingqi Fan2, Anhao Zhao2,Hui Su5,Xiaoyu Shen2*, 1Shanghai Jiao Tong University 2Ningbo Key Laboratory of Spatial Intelligence and Digital... | https://arxiv.org/abs/2505.16983v1 |
for streaming involves iteratively re-encoding both new inputs and prior outputs with each incoming data segment (Agostinelli et al., 2024; Wang et al., 2024; Guo et al., 2024b; Koshkin et al., 2024), as illustrated in Figure 1(b). While this batch-streaming paradigm preserves compatibility with batch-processing ar- ch... | https://arxiv.org/abs/2505.16983v1 |
on batch architectures( group- streaming ), which groups input and output position ids to enable more consistent processing with the batch model. This strategy is not only computa- tionally efficient but also generalizable across dif- ferent tasks and model architectures. We validated its effectiveness on cross-lingual... | https://arxiv.org/abs/2505.16983v1 |
the time, which may lead to inconsistencies com- pared to batch-mode processing.Position-ID Mismatch In batch-streaming, to- kens receive contiguous position IDs by position re-encoding, so that for an input sequence Xtand output sequence Yt′, we have: p(xi) =i, p (yj) =t+j, (5) ensuring that the relative positional di... | https://arxiv.org/abs/2505.16983v1 |
to performance degradation. Effects of Position-ID Mismatch Re-encoding can address the remaining two mismatches. We further decompose re-encoding into two compo- nents: KV cache re-encoding and position embed- ding re-encoding. The former enables target to- kens to attend to the most recently available tokens, thereby... | https://arxiv.org/abs/2505.16983v1 |
analysis suggests that positional mis- matches do not significantly impact the perfor- mance of streaming tasks. To further elucidate this phenomenon, this section provides a detailed inves- tigation into the impact of positional encoding on the performance of LLMs in streaming scenarios. 4.1 Is Position Encoding Neces... | https://arxiv.org/abs/2505.16983v1 |
41.92 41.92 42.03 41.94 41.93 0.11 32.26 32.26 32.23 32.33 32.28 0.10 LLama3.1-8B-Instruct5 40.11 40.11 40.10 39.93 39.92 0.19 30.33 30.33 30.21 30.37 30.34 0.16 7 40.30 40.30 40.32 40.35 40.31 0.03 31.23 31.23 31.18 31.16 31.25 0.09 9 40.15 40.15 40.32 40.34 40.35 0.20 31.80 31.80 31.83 31.76 31.89 0.13 11 40.53 40.53... | https://arxiv.org/abs/2505.16983v1 |
settings yield comparable performance, suggesting that po- sitional overlap appears to have limited impact on Wait-kSpeech-Text (Target start id ϕ) 0 256 512 1024 2048 ∆ 1 6.02 6.05 6.04 6.07 6.17 0.15 3 4.12 4.10 4.09 4.08 4.19 0.11 5 3.52 3.58 3.55 3.59 3.61 0.09 7 3.33 3.33 3.38 3.41 3.45 0.12 Table 4: Performance o... | https://arxiv.org/abs/2505.16983v1 |
source information during inference. Notably, we normalize the attention weights column-wise (i.e., across each source token) to the range [0, 1]. This normalization offers two key benefits: (1) it miti- gates the influence of tokens with inherently large absolute attention values and highlights the relative importance... | https://arxiv.org/abs/2505.16983v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.