text string | source string |
|---|---|
Tarjama-25addresseskeylimitationsofexisting datasets, such as short sentence length, English source bias, and limited domain diversity. It comprises 5,000 pairs of expert-curated sentences from diverse domains, with an equal number of examples sourced from Arabic and English originals. All pairs are used to evaluate bo... | https://arxiv.org/abs/2505.17894v1 |
for Arabic translation. Despite strong zero-shot transfer capabilities, mT5 struggles with language-specific nuances, prompting further specialization in later models. Similarly, Aya-101 Üstün et al. [2024] adapts the mT5-XXL model (13B parameters) using instruction tuning in 100+ languages. This broad multilingual tun... | https://arxiv.org/abs/2505.17894v1 |
translation system that demonstrated strong performance in both MSA and dialectal Arabic. Lahjawi is specifically undergoing targeted fine-tuning for cross-dialect translation. Given the trade-off between translation quality, inference speed, and resource efficiency, in this work, we adopt the decoder-only paradigm. Mu... | https://arxiv.org/abs/2505.17894v1 |
diverse topics while preserving high translation quality. 4 Tarjama-25: Bidirectional Arabic-English Translation Benchmark 4.1 Motivation and Development Modern MT systems face persistent evaluation challenges due to the limitations of existing bench- marks. To address these gaps, we introduce Tarjama-25 , a comprehens... | https://arxiv.org/abs/2505.17894v1 |
for translation tasks, we further pre-trained our model on English-Arabic parallel data using a next-token prediction objective. To facilitate the learning process, we introduce two special tokens to our model: <|English|> and <|Arabic|> . We formatted the data as shown on the left side of Figure 3, where English sente... | https://arxiv.org/abs/2505.17894v1 |
[2020] and chrF++ metrics on the WMT24++ benchmark Deutsch et al. [2025]. Despite being exposed to more diverse data, the bidirectionalmodelshowedaslightdecreaseinperformance. Unidirectionalmodelsconsistentlyout- performed the bidirectional model, with Mutarjim-AR2EN achieving a COMET score 3.16 points higher than Muta... | https://arxiv.org/abs/2505.17894v1 |
50.84 — — Mutarjim-EN2AR-e2 — — 73.56 46.05 Table3: Evaluationofmodelsfine-tunedwithdifferentinputlengthdistributionsontheWMT24++ test set. 7 Evaluation To contextualize the performance of Mutarjim , we compare it against a diverse set of strong decoder-onlymodelsthatsupportArabicandarewidelyrecognizedfortheirtranslati... | https://arxiv.org/abs/2505.17894v1 |
Mutarjim 1.5B 82.63 74.66 55.28 83.41 68.67 43.71 NLLBCosta-Jussà et al. [2022b] 3.3B 67.06 40.50 24.38 81.27 59.69 30.32 c4ai Cohere For AI [2024] 7B 80.93 67.24 43.34 79.10 55.96 25.18 Yehia Navid-AI [2025] 7B 73.31 56.77 32.14 74.97 50.32 20.67 ALLamBari et al. [2024] 7B 72.90 56.88 31.01 75.41 51.24 20.54 Cohere Ar... | https://arxiv.org/abs/2505.17894v1 |
- 48.56 22.28 1.57 Cohere Aryabumi et al. [2024] 32B 84.30 59.02 35.37 74.63 43.53 8.93 GPT-4o mini Hurst et al. [2024] - 86.37 60.48 36.86 87.14 47.63 15.50 Table 6: Performance comparison of bidirectional (Arabic-English) translation models on the IWSLT-2017 benchmark in terms of COMET, Chrf++, and Bleu. 8 Conclusion... | https://arxiv.org/abs/2505.17894v1 |
Mara Finkelstein, Rebecca Galor, Juraj Juraska, Geza Kovacs, Alison Lui, Ricardo Rei, Jason Riesa, et al. Wmt24++: Expanding the language coverage of wmt24 to 55 languages & dialects. arXiv preprint arXiv:2502.12404 , 2025. Mohamed Motasim Hamed, Muhammad Hreden, Khalil Hennara, Zeina Aldallal, Sara Chrouf, and SafwanA... | https://arxiv.org/abs/2505.17894v1 |
Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, and ... | https://arxiv.org/abs/2505.17894v1 |
and (b) base into the formula: arcsin/parenleftBig√ 2b 2l/parenrightBig =arcsin/parenleftBig√ 8h2+2b2 4h/parenrightBig . This will give you the angle of the pyramid from the apex to the base edge.(ﻉافتﺭالﺍميقﺽّوع h ) (ﺓدعاقلﺍو b ) :ةغيصلﺍيف arcsin/parenleftBig√ 2b 2l/parenrightBig =arcsin/parenleftBig√ 8h2+2b2 4h/paren... | https://arxiv.org/abs/2505.17894v1 |
T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation Zi-Ao Ma1∗, Tian Lan1∗, Rong-Cheng Tu2, Shu-Hang Liu1, Heyan Huang1,Zhijing Wu1,Chen Xu3†,Xian-Ling Mao1† 1School of Computer Science and Technology, Beijing Institute of Technology, China 2Nanyang Technological University, ... | https://arxiv.org/abs/2505.17897v1 |
recent work has turned to training open-source MLLMs through supervised fine-tuning (SFT), aiming to replicate the evaluation ability of commercial models while avoiding their cost and constraints. For instance, EATG [ 31] formulates the evaluation task into sub-skills such as object presence, attribute correctness, an... | https://arxiv.org/abs/2505.17897v1 |
high computational overhead and rely on handcrafted pipelines. More recently, multimodal LLMs (MLLMs) have been applied directly as evaluators, generating natural-language rationales alongside scalar judgments. For example, VIEScore prompts GPT-4o to 2 produce chain-of-thought critiques that align closely with human pr... | https://arxiv.org/abs/2505.17897v1 |
anchor descriptions, or relational criteria). We define an evaluator: E: (P, I or(IA, IB), D, G )7−→(r, q) (1) where the outputs are: (1) r, a chain-of-thought rationale in natural language; (2) q, a quantitative judgment, which may take one of two forms: a single-image score s∈[smin, smax]for single-wise evaluation; o... | https://arxiv.org/abs/2505.17897v1 |
preference data and are not able to make full use of single-wise annotated data during training, bringing about limitations to its broader applications to some extent. MLE Objective By contrast, generative evaluators frame T2I evaluation as sequence prediction and are typically trained with a maximum likelihood estimat... | https://arxiv.org/abs/2505.17897v1 |
and guidelines, we obtain a 36,000-sample dataset, and each sample is associated with a reference score ranging from 0 to 10. This balanced sampling ensures uniform coverage across dimensions during policy learning and avoids over-representation of any single aspect. 5 Pairwise Evaluation Corpus Our pairwise dataset is... | https://arxiv.org/abs/2505.17897v1 |
is trained with the full single-wise T2I-Eval dataset mentioned in Section 3.3. This model can used for either single-wise evaluation or pairwise evaluation in the single-wise manner; •T2I-Eval-R1 Enhance : On the basis of T2I-Eval-R1 Base, we further perform rejection sampling on the T2I-Eval dataset, resulting in a s... | https://arxiv.org/abs/2505.17897v1 |
proprietary (GPT-4o–based) and open-source baselines. It is worth noting that our method is sinifi- cantly ahead of previous baselines in intrinsic and relationship attribute consistency, showing great capabilities in learning human preference from simple coarse-grained annotated scores. This validates that T2I-Eval-R1... | https://arxiv.org/abs/2505.17897v1 |
GRPO. MethodAppearance Intrinsic Relationship Overall ρ τ ρ τ ρ τ ρ τ T2I-Eval-R1 Base 47.07 35.15 52.10 40.98 50.46 39.73 58.13 42.76 T2I-Eval-R1 Enhance 47.68 36.20 51.69 40.72 51.31 40.43 58.74 43.80 To validate the effectiveness of the proposed rejection sampling and further GRPO of T2I-Eval- R1Enhance , we compare... | https://arxiv.org/abs/2505.17897v1 |
the T2I-Eval benchmark, we prompted GPT-4o to score each method’s rationale for clarity, completeness, and fidelity to the reference explanation. The results are illustrated in Figure 1. Overall wins : T2I-Eval-R1 achieved the highest average quality score in the Overall evaluation, outperforming LLMScore, VIEScore, an... | https://arxiv.org/abs/2505.17897v1 |
reward functions, the optimized models yield interpretable evaluations that align more closely with human judgments than prior approaches across diverse dimensions. Extensive experiments demonstrate that T2I-Eval-R1 not only matches or exceeds GPT-4o-based baselines in correlations with human judgements, but also gener... | https://arxiv.org/abs/2505.17897v1 |
, F., & others (2024) Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning [9]Fu , S., Tamir , N., Sundaram , S., Chai , L., Zhang , R., Dekel , T., & Isola , P. (2023) Dreamsim: Learning new dimensions of human visual similarity using synt... | https://arxiv.org/abs/2505.17897v1 |
Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) pages 12268–12290. [21] Li , J., Li , D., Savarese , S., & Hoi , S. (2023) Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning pages... | https://arxiv.org/abs/2505.17897v1 |
Zang , Y ., Li , H., Jin , C., & Wang , J. (2025. ) Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236 [34] Welleck , S., Kulikov , I., Roller , S., Dinan , E., Cho , K., & Weston , J. (2020) Neural text degeneration with unlikelihood training. In 8th International Confere... | https://arxiv.org/abs/2505.17897v1 |
of approximately $5.15 USD, which exceeds the average hourly wage of $3.13 USD on Amazon Mechanical Turk [12]. C Benchmark Datasets We assess our models trained with Eval-GRPO on three public benchmarks, each targeting a distinct evaluation mode: •T2I-Eval [31] (under MIT License): Contains coarse human annotated score... | https://arxiv.org/abs/2505.17897v1 |
goal: {dimensions}.This evaluation focuses on the following criteria:{dimension_explanations} You should make a well-reasoned judgment based on these criteria.# Annotation Input# Evaluation Guidelines-Carefully analyze the generated output(s) in relation to the input data and defined evaluation criteria.-Consider the o... | https://arxiv.org/abs/2505.17897v1 |
quality of text-to-image generative tasks. Your role is to evaluate the generated image according to the specified evaluation goal: intrinsic attribute consistency . This evaluation focuses on the following criteria: * What we mean by “intrinsic attribute” is that the attributes are properties of the entity explicitly ... | https://arxiv.org/abs/2505.17897v1 |
at all. - 4-7: The generated attribute is somewhat consistent with the text. Semantics are similar but not entirely consistent. - 8-10: The generated attribute is very consistent with the text. # Output Format Produce a response of a single floating-point number between 0.0 and 10.0 based on the evaluation criteria as ... | https://arxiv.org/abs/2505.17897v1 |
of text-to-image generative tasks. Your role is to evaluate the generated image according to the specified evaluation goal: text-to-image faithfulness . This evaluation focuses on the following criteria: * What we mean by “relationship attribute” is that the attributes describe the entity’s relationship with other enti... | https://arxiv.org/abs/2505.17897v1 |
the image are different from the text description, for example, generating an image of “a little girl sitting in front of a sewing machine” with many little girls is incorrect. * What we mean by “fidelity” is that the generated image should be true to the shape and characteristics of the object, and not generated hapha... | https://arxiv.org/abs/2505.17897v1 |
21 Thephotoperspectiveoffersareflectionshotofamechanic,intentlytroubleshootinganelectricalissue.-Question1:Isthemechanicintentlyworkingontheelectricalissue?-Answer:Bothmechanicsarefocusedonthetaskathand,withoneholdingthecarinplacewhiletheotherappearstobeworkingwiththetools,suggestingtheyareworkingontheissueintently.-Ex... | https://arxiv.org/abs/2505.17897v1 |
arXiv:2505.17923v1 [cs.CL] 23 May 2025Language models can learn implicit multi-hop reasoning, but only if they have lots of training data Yuekun Yao Saarland University ykyao@coli.uni-saarland.deYupei Du Utrecht University y.du@uu.nlDawei Zhu Saarland University dzhu@lsv.uni-saarland.de Michael Hahn∗ Saarland Universit... | https://arxiv.org/abs/2505.17923v1 |
is Robert ) and knowledge-based ques- tions (e.g. Who is the instructor of the instructor of Jennifer? ), we study if such language models learn to generalize to questions that require novel combinations of learned facts. Our study addresses three research questions. •First, can LMs learn implicit k-hop reason- ing, an... | https://arxiv.org/abs/2505.17923v1 |
which al- lows us to accurately attribute the model behavior to particular aspects like data and models. Wang et al. (2024) also train a transformer on synthetic datasets to evaluate 2-hop reasoning. By contrast, we investigate this question across increasingly complex tasks (e.g. 2,3,4-hop), and we shed light on possi... | https://arxiv.org/abs/2505.17923v1 |
and so on as the 1-hop, 2-hop, and subsequent hops, respectively. We thus call e′ 1the1-hop entity, and r1the1-hop relation. While prior work has mostly focused on 2-hop queries involving a single bridge entity, we construct datasets for k∈ {2,3,4}to assess mod- els’ ability to handle increasingly complex reason- ing c... | https://arxiv.org/abs/2505.17923v1 |
budgets. Empty cells indicate that the data budget exceeds the number of possible questions. entity’s profile. To construct reasoning questions, we sample entities from the bottom layer of the hierarchy (Figure 3) and recursively traverse krela- tions to identify the correct answer. All valid k-hop queries are generate... | https://arxiv.org/abs/2505.17923v1 |
model with the prompt up to the an- swer token (e.g., “ Who is the instructor of the in- structor of Jennifer? \n Answer: ”) and evaluate the accuracy of the generated token against the gold answer. Greedy decoding is used for evaluation. 4.2 Results Language models can learn k-hop reasoning. Ta- ble 1 reports the test... | https://arxiv.org/abs/2505.17923v1 |
Fixing 1-hop and 2-hop relations reduces the required training budget to ×1, while increasing them leads to rapid budget growth. 4.3 Why data-hungry? Results so far highlight the substantial data require- ments for k-hop tasks, but the reason for this re- mains unclear. Increasing the value of kleads to both an increas... | https://arxiv.org/abs/2505.17923v1 |
the probe classifiers. Causal intervention. While probing shows whether information about bridge entities is en- coded in the hidden representations, it does not tell us whether the model actually relies on this infor- mation to generate the final answer. We further design activation patching (Vig et al., 2020; Meng et... | https://arxiv.org/abs/2505.17923v1 |
3% 2% 100% 40% 2% 1% 24% 4% 3% 3% 27% 3% 1% 2% 38% 93% 100% 100% 96% 5% 2% 1% 67% 5% 2% 2% 100% 41% 2% 1% 24% 2% 2% 3% 34% 4% 2% 1% 39% 94% 100% 99% 96% 6% 2% 1% 67% 5% 2% 1% 100% 44% 3% 1% 25% 3% 2% 4% 35% 5% 2% 2% 42% 95% 100% 95% 96% 6% 2% 2% 68% 4% 2% 2% 100% 46% 3% 2% 23% 2% 2% 2% 41% 4% 1% 2% 50% 98% 100% 82% 97%... | https://arxiv.org/abs/2505.17923v1 |
prior observations from 2-hop tasks (Biran et al., 2024; Wang et al., 2024). 5.3 Theoretical Analysis We have found that language models perform the k-hop task by layer-wise lookup. This suggests that transformers may need depth linear in the number of reasoning steps. Here, we discuss how this result relates to the in... | https://arxiv.org/abs/2505.17923v1 |
task, but i-hop ( i < k ) questions should also be available in realistic setups. By ex- ploiting such easier questions as additional training data for k-hop task, we demonstrate that curricu- lum learning significantly mitigates the exponential growth issue, though not eliminate the increase of data budget as kincreas... | https://arxiv.org/abs/2505.17923v1 |
For example, curriculum learning requires ×2bud- get for 3-hop task and ×5for4-hop task, indicating the challenge of k-hop implicit reasoning for LMs. 7 Conclusion Our work investigates whether language models can learn implicit multi-hop reasoning. We provide a nuanced answer through controlled k-hop rea- soning datas... | https://arxiv.org/abs/2505.17923v1 |
arXiv:2412.21187 . Yuntian Deng, Yejin Choi, and Stuart Shieber. 2024. From explicit cot to implicit cot: Learning to internalize cot step by step. arXiv preprint arXiv:2405.14838 . Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lor- raine Li, Liwei Jiang, Bill Yuchen Lin, Sean Welleck, Peter West, Chandra Bhagavatula, R... | https://arxiv.org/abs/2505.17923v1 |
2023. The par- allelism tradeoff: Limitations of log-precision trans- formers. Transactions of the Association for Compu- tational Linguistics , 11:531–545.Shikhar Murty, Pratyusha Sharma, Jacob Andreas, and Christopher Manning. 2023. Grokking of hierarchi- cal structure in vanilla transformers. In Proceedings of the 6... | https://arxiv.org/abs/2505.17923v1 |
Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier- ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. 2019. Huggingface’s transformers: State-of- the-art natural language processing. arXiv preprint arXiv:1910.03771 . Sohee Yang, Elena Gribovskaya, Nora Kassner, Mor Geva, and Seba... | https://arxiv.org/abs/2505.17923v1 |
equals it- self). To conclude the theorem, the remaining prob- lem is now to show that there is a way of choosing Rfor which the right-hand-side scales with k. We arbitrarily label the elements of Eas {0, x0, x1, . . . , x n−1}, and define R={f, g} where: f(0) =0 f(xi) =x(i+1)% n g(0) =0 g(x0) =0 g(xi) =xi(i >0) Intuit... | https://arxiv.org/abs/2505.17923v1 |
layers, but does not bound how many layers are needed. Bounds from NC1-hardness As transformers can be simulated in TC0(e.g. Merrill and Sabhar- wal, 2023; Strobl, 2023), some work has obtained bounds conditional on standard complexity con- jecture TC0̸=NC1. Assuming this conjecture, transformers generally cannot solve... | https://arxiv.org/abs/2505.17923v1 |
with enough data budget, e.g. for 3-hop, model accuracy gets signifi- cantly improved accuracy at ×5budget and reaches 100% at×10budget. We consider the lower accu- racy here is likely due to the lack of hyperparameter optimization and use of better position encoding. B.2 Scaling up the model size. We also evaluate set... | https://arxiv.org/abs/2505.17923v1 |
small) in each training set. We partition the |E|entities into 5 disjoint subsets, each containing 5https://chatgpt.com/ Training data budget Dataset ×1 ×2 ×5 ×10 ×20 ×50 ×100 k-hop small2-hop 93.7 3-hop 6.6 8.2 45.4 100 4-hop 5.1 6.5 6.9 8.4 23.8 100 100 k-hop large2-hop 100 3-hop 2.8 2.5 3.9 87.5 100 4-hop 2.3 3 4.1 ... | https://arxiv.org/abs/2505.17923v1 |
heads. The input embedding di- mension is 768, and the context window is limited to 1024 tokens. Instead of absolute position embed- dings used in the original Transformer (Vaswani et al., 2017), we employ Rotary Position Embed- ding (RoPE) (Su et al., 2024) to encode positional information. We use the default GPT-2 to... | https://arxiv.org/abs/2505.17923v1 |
base- line and mixed learning. E.2 Standard deviation For each experiment reported in Section 4 and 6, we made 3 runs based on different random seeds. We report the mean and standard deviation of the test accuracy for each model in Table 8. For most results we do not observe a large standard deviation, indicating that ... | https://arxiv.org/abs/2505.17923v1 |
patching replacing the residual stream of a particular layer across prompt tokens. Whoisthe<r4>ofthe<r3>ofthe<r2>ofthe<r1>of <space> <Entity>?\n Answer: <space>123456789101112Layer 0.00.20.40.60.8 Effect size Figure 13: Results for activation patching replacing the MLP output of a particular layer across prompt tokens.... | https://arxiv.org/abs/2505.17923v1 |
development, allowing higher-hop circuits to build upon existing lower-hop circuits, explaining the observed effectiveness in Section 6. Curriculum learning has also been explored in prior work (Deng et al., 2024; Hao et al., 2024), where the focus is on internalizing explicit rea- soning abilities. These studies start... | https://arxiv.org/abs/2505.17923v1 |
arXiv:2505.17928v2 [cs.SE] 28 May 2025Towards Practical Defect-Focused Automated Code Review Junyi Lu1 2 †Lili Jiang3Xiaojia Li3Jianbing Fang4 †Fengjun Zhang1Li Yang1Chun Zuo5 Abstract The complexity of code reviews has driven ef- forts to automate review comments, but prior ap- proaches oversimplify this task by treat... | https://arxiv.org/abs/2505.17928v2 |
key challenges (Appendix C): Capturing Proper Code Context: Effective review requires analyzing dependencies beyond the immediate diff hunk (e.g., variable declarations or method calls). However, exces- sively long inputs degrade LLM performance, necessitating efficient context extraction. Improving Key Bug Inclusion (... | https://arxiv.org/abs/2505.17928v2 |
summarizing findings in Section D. Background on code slicing and multi-role systems, key techniques in our work, is introduced in Sections E and F. 3. Proposed Approach 3.1. Overview Figure 2 illustrates our decoupling process of code review automation architecture: 1) Code Slicing : Extracting code from the diff hunk... | https://arxiv.org/abs/2505.17928v2 |
the final comments into the required language for multinational teams, ensuring proper formatting for direct integration into the development environment. Each role is integrated with Chain-of-Thought technique, as detailed in Section H.3.4. Redundancy Comment Filter Mechanism LLMs often produce an overwhelming number ... | https://arxiv.org/abs/2505.17928v2 |
in prior work is the precise localization of comments within the code. Unlike code sum- marization tasks, code reviews require pinpointing specific lines of code where issues are identified. Without this in- formation, developers face inefficiencies in verifying and addressing comments. For example, the change-involved... | https://arxiv.org/abs/2505.17928v2 |
includes: LLaMA-3.1 (70B), Qwen2 (72B), Command R+ (104B), Mistral-large- 2407 (123B), and LLaMA3.1 (405B). The reasons for not selecting other models are outlined in Section L. 4.3. Metrics In accordance with the real-world developer expectations discussed in Section D, we evaluate performance at the merge request (MR... | https://arxiv.org/abs/2505.17928v2 |
46 .67 0 .00 – – Qwen2 (72B)w/o 42.22 90 .99 14 .86 83 .91 23 .30 w 28.89 91 .73 12 .86 79 .06 24 .28 Command R+ (103B)w/o 15.56 94 .22 8 .43 77 .14 18 .51 w 8.89 76 .30 12 .93 58 .33 14 .65 Mistral-2407 (123B)w/o 28.89 90 .68 14 .09 75 .44 26 .55 w 28.89 86 .11 18 .76 67 .30 30 .68 LLaMA3.1 (405B)*w/o 31.11 89 .41 15 ... | https://arxiv.org/abs/2505.17928v2 |
that while our framework does not employ an explicit Retrieval-Augmented Gener- ation (RAG) pipeline, our code slicing mechanism is de- signed with a RAG-aligned objective. Specifically, it serves a similar purpose to RAG by strategically retrieving and providing the LLM with only the most relevant contextual code ’sli... | https://arxiv.org/abs/2505.17928v2 |
conduct experiments on: ❶Leveraging the non-determinism of large language models; ❷The self- correction capability (validator); ❸The chain-of-thought (CoT) prompting strategy. 5.3.1. N UMBER OF REVIEWERS Previous research has shown that the non-determinism of large language models (LLMs) can impact results. Specifi- ca... | https://arxiv.org/abs/2505.17928v2 |
.70 11 .26 55 .56 11 .59 3 11.11 89 .48 10 .81 65 .33 16 .83 Left Flow + Meta Reviewer1 26.67 83 .26 20 .57 70 .56 27 .99 3 31.11 87 .81 17 .51 67 .98 31 .56 + Validator1 11.11 69 .26 16 .32 23 .33 19 .41 3 20.00 75 .37 22 .07 43 .52 29 .54 Full Flow + Meta Reviewer1 22.22 78 .04 22 .09 71 .17 25 .10 3 31.11 89 .41 15 ... | https://arxiv.org/abs/2505.17928v2 |
89 .09 13 .52 w/ 13.33 96 .74 5 .24 20 .00 92 .41 11 .01 MR - Valw/o 6.67 63 .89 11 .26 11 .11 75 .19 15 .35 w/ 11.11 90 .11 10 .46 11 .11 89 .48 10 .81 Left Flow Full Flow SR - Allw/o 34.81 95 .16 8 .49 40 .00 94 .40 9 .83 w/ 37.04 94 .36 9 .77 39 .26 94 .48 9 .67 SR - Top-5w/o 20.74 92 .37 11 .10 20 .74 91 .94 11 .50... | https://arxiv.org/abs/2505.17928v2 |
13 .33 91 .60 10 .23 Multi+ Meta 31.11 87 .81 17 .51 31 .11 89 .41 15 .80 + Validator 20.00 75 .37 22 .07 20 .00 77 .96 20 .97 ing (Left Flow, Full Flow), adding these filters sequentially decreases FAR 1and improves CPI 1. In simpler slicing (Original Diff, Parent Function), only the coarse filter proves particularly ... | https://arxiv.org/abs/2505.17928v2 |
to streamline the task. Another ap- proach, CommentFinder (Hong et al., 2022), presented an efficient retrieval-based model tailored to new code. More recently, LLaMA-Reviewer (Lu et al., 2023) trained large language models specifically for code review tasks, and DISCOREV (Ben Sghaier & Sahraoui, 2024) improved perform... | https://arxiv.org/abs/2505.17928v2 |
to reduce nitpicks and hallu- cinations more effectively. ❹Streamlining pipeline to make automation more accessible. Limitation. We discuss limitations in Section V. Data Availability. We publicly release our codes at https: //zenodo.org/records/14779175 . Details regard- ing their open-source status can be found in Se... | https://arxiv.org/abs/2505.17928v2 |
programming in your terminal, 2024. URL https://github.com/ paul-gauthier/aider . Accessed: 2024-09-12. Guo, T., Chen, X., Wang, Y ., Chang, R., Pei, S., Chawla, N., Wiest, O., and Zhang, X. Large language model based multi-agents: A survey of progress and challenges. In 33rd International Joint Conference on Artificia... | https://arxiv.org/abs/2505.17928v2 |
Wang, S., Liu, Z., Liu, Y ., Xia, X., and Mao, X. Cct5: A code-change-oriented pre-trained model. In Pro- ceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering , 2023. Lin, C.-Y . Rouge: A package for automatic evaluation of summaries. In Text summarization branches out , pp. 74–81, 2... | https://arxiv.org/abs/2505.17928v2 |
conference on Software engineering , pp. 541–550, 2008. Rigby, P. C., German, D. M., Cowen, L., and Storey, M.-A. Peer review on open-source software projects: Parame- ters, statistical models, and theory. ACM Transactions on Software Engineering and Methodology (TOSEM) , 23(4): 1–33, 2014. Sadowski, C., S ¨oderberg, E... | https://arxiv.org/abs/2505.17928v2 |
pp. 460–463, 2016. Yu, L., Lu, J., Liu, X., Yang, L., Zhang, F., and Ma, J. Pscvfinder: a prompt-tuning based framework for smart contract vulnerability detection. In 2023 IEEE 34th Inter- national Symposium on Software Reliability Engineering (ISSRE) , pp. 556–567. IEEE, 2023. Yu, L., Chen, S., Yuan, H., Wang, P., Hua... | https://arxiv.org/abs/2505.17928v2 |
urgent and practical need for more effective defect detection. These expectations were extracted from the Objectives and Key Results set by approximately 50 experienced super reviewers (the concept comes from Kononenko et al.(Kononenko et al., 2016)) within a major production environment of 4000+ developers. In conclus... | https://arxiv.org/abs/2505.17928v2 |
of each comment directly at the relevant line number(s) in the diff view of the MR. This is achieved by accurately parsing diff hunks and mapping comment locations. The effectiveness and importance of this line-aware comment injection for providing clear, contextualized, and actionable feedback was specifically evaluat... | https://arxiv.org/abs/2505.17928v2 |
snippet (McAleese et al., 2024). In real-world scenarios, merge requests often contain numerous code snippets, and managing redundant comments can overwhelm human reviewers. Most previous studies (Gupta & Sundaresan, 2018; Siow et al., 2020; Tufano et al., 2021; 2022; Li et al., 2022a; Hong et al., 2022) have not addre... | https://arxiv.org/abs/2505.17928v2 |
correct code lines. This aids reviewers or code owners in efficiently verifying issues and prevents confusion or misleading information, a factor captured by our Line Localization Success Rate (LSR). The demand D2aligns with Challenge 1 (Capturing Relevant Context) from the Introduction, while expectations E1, E2, and ... | https://arxiv.org/abs/2505.17928v2 |
et al., 2025). Given that LLMs now often include code in their training corpora, they have developed strong abilities in code-related tasks alongside their general language capabilities. This blurs the line between code-specific and general models. For instance, GPT-4 excels in code generation, while models like ChatGP... | https://arxiv.org/abs/2505.17928v2 |
slices 4: clone repository and checkout to commit 5:ASTs ←ApplyStaticAnalysisTool(repository) 6:cache←InitializeCache() 7:slices ←[]{Initialize slice list } 8: foreachAST inASTs do 9: ProcessAST( AST , slicingOption, cache) 10: end for 11: while not cache.isEmpty() do 12: seed←GetContiguousDiffSegment (cache ) 13: newS... | https://arxiv.org/abs/2505.17928v2 |
Your Thoughts: Directs the model to write a detailed review comment specifying the issue, affected lines, root cause, recommended solution, and example code. 6.Final Comment: Instructs the model to output the final comment in JSON format. For the Meta-Reviewer: 1.System Introduction: Introduces the task of merging Revi... | https://arxiv.org/abs/2505.17928v2 |
effectiveness of four slicing algorithms and study the results using a Venn diagram. This analysis focuses primarily on KBI and CPI, particularly the ability to recall key bugs. RQ3: How do the different components of the multi-role system impact the performance of our framework? This question explores the influence of... | https://arxiv.org/abs/2505.17928v2 |
for comprehensive understanding (Lu et al., 2025). These limitations reduce its applicability to real-world, defect-focused code review automation. To provide context, we compare our dataset’s scale with that of CodeReviewer. Table 9 juxtaposes the size and complexity of the datasets, demonstrating that ours is of comp... | https://arxiv.org/abs/2505.17928v2 |
on high-impact defects rather than trivial concerns. KBI measures the model’s ability to recall key issues that cause system faults. It is calculated as the percentage of recalled key issues out of the total issue set: KBI=Number of recalled key issues Total number of key issues×100 (1) 23 Towards Practical Defect-Focu... | https://arxiv.org/abs/2505.17928v2 |
Diff Parent Function Left Flow Full Flow Slicing Algorithms010min20min30min40min50min60min70min80min90min100minRuntime (min) 4.8min7.7min6.2min 6.3min Figure 5. Runtime per merge request under different slicing algorithms and LLaMA3.1-405B as base models. The most time-consuming algorithm is Function , due to its inclu... | https://arxiv.org/abs/2505.17928v2 |
in understanding the overarching code logic and intent. Performance issues remain the most difficult to detect, as they tend to be subtle and delayed in manifestation. Q. Discussion on High FAR The initially reported False Alarm Rate (FAR) in Table 2 appears relatively high. This is partly due to our strict definition:... | https://arxiv.org/abs/2505.17928v2 |
for the four slicing algorithms under various stages of the single- reviewer filtering pipeline. As emphasized in our response to reviewer feedback, the ”Single Reviewer – All” setting is particularly insightful, as it reflects the unfiltered, raw output from the Large Language Model when provided with context from dif... | https://arxiv.org/abs/2505.17928v2 |
Left Flow (24.44, 40.00) (91.75, 92.20) (11.83, 13.68) (77.17, 90.38) (15.15, 23.61) Full Flow (31.11, 33.33) (91.73, 93.78) (10.48, 13.07) (87.69, 90.70) (14.54, 17.64) Single Reviewer – Top-10 Original Diff (13.33, 20.00) (84.83, 91.81) (10.26, 17.26) (70.83, 79.69) (18.30, 20.15) Parent Function (13.33, 22.22) (87.4... | https://arxiv.org/abs/2505.17928v2 |
that while the optimal kcan be tuned, the Top-k filter’s behavior is generally stable across reasonable threshold ranges. Furthermore, it is adaptable to the context richness provided by different slicing algorithms, allowing for optimized configurations based on the desired balance between metrics like KBI and FAR. T.... | https://arxiv.org/abs/2505.17928v2 |
the added computational cost and need for validation must be considered in practical implementations. Conclusion 3.2 (Original) The self-correction ability of LLMs, as implemented by the validator role, improves precision by reducing false alarms ( FAR 1andFAR 2) but may reduce key bug inclusion ( KBI ). This indicates... | https://arxiv.org/abs/2505.17928v2 |
These components do not inherently rely on C++-specific features. Consequently, extending the framework to support other compiled languages is considered feasible, mainly requiring the integration of suitable language-specific AST parsing tools or static analyzers. Another potential threat arises from how we calculate ... | https://arxiv.org/abs/2505.17928v2 |
arXiv:2505.17936v1 [cs.LG] 23 May 2025Understanding Gated Neurons in Transformers from Their Input-Output Functionality Sebastian Gerstner and Hinrich Schütze Center for Information and Language Processing (CIS), LMU Munich, and Munich Center for Machine Learning (MCML), Germany sgerstner@cis.lmu.de Abstract Interpreta... | https://arxiv.org/abs/2505.17936v1 |
least approximately points in one of these di- rections in model space), corresponding to its weight vectors on the input side; and then writes to a certain direction, corresponding to its output weight vector. A semantic intepretation is that a neuron detects a concept in the residual stream (for example, an inter- me... | https://arxiv.org/abs/2505.17936v1 |
6). (vi) We propose theoretical explanations for some of these results (Section 7). 2 Related Work There is a large body of work on interpretability of transformer-based LLMs. Elhage et al. (2021) introduce the notion of residual stream. nostalgebraist (2020), Bel- rose et al. (2023) propose to interpret residual strea... | https://arxiv.org/abs/2505.17936v1 |
(Section 3.1) and properties (Section 3.2) of these functions. Gated acti- vation functions are used widely, e.g., OLMo (Groen- eveld et al., 2024) and Llama (Touvron et al., 2023) use SwiGLU, and Gemma (Gemma, 2024) uses GeGLU. The following description focuses on SwiGLU. GeGLU replaces Swish with GeLU, but is otherwi... | https://arxiv.org/abs/2505.17936v1 |
is positive.) Roughly, we can distinguish three cases: the neuron output (determined by wout) can be similar to the input direction (in our case, review : we call this enrichment ), different (we call this orthog- onal output ), or roughly opposite (in our case, “minus review ”: we call this depletion ). In terms of we... | https://arxiv.org/abs/2505.17936v1 |
subspace but have different orientations), the neuron will write “minus review ”. We call this (typical) depletion .2The same neurons can also get a weak negative activation if −wgate(“minus review ”) is weakly present in the residual stream. In this case, Swish has a negative value (Section 3.2) and the enrichment neu... | https://arxiv.org/abs/2505.17936v1 |
) and thus be be similar to an enrichment neuron in terms of weight vector geometry. For this general case, this paper explores three options to understand neuron IO functionalities at different lev- els of granularity: (1) Classify neurons according to the closest prototypical case. (2) Plot the marginal distribu- tio... | https://arxiv.org/abs/2505.17936v1 |
see that a large proportion of neurons are input manipulators (i.e., they are not orthogonal output neu- rons): in the Llama model, these are 25% of all neurons, and as much as 50% in early-middle layers (layers 7–11). This highlights an advantage of our parameter-based IO classes: It is an exhaustive analysis of all n... | https://arxiv.org/abs/2505.17936v1 |
vector configurations in de- tail, as shown in Figure 5 for a few selected layers. The distribution of neurons in each layer is plotted by displaying each neuron as a point with cos(wgate, wout) indicated on the x-axis, cos(win, wout)on the y-axis and cos(wgate, win)as its color. This visualization reinforces three fin... | https://arxiv.org/abs/2505.17936v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.