text string | source string |
|---|---|
a fixed set of pruning factors. As these computations are independent, they can be performed in parallel. The GA initializes and mutates chromosomes by selecting from this precomputed set. During fitness evaluation, each chromosome is used to instantiate a separate LLM with the corresponding matrices, enabling parallel... | https://arxiv.org/abs/2505.18350v1 |
5 reports the percentage reduction in model size across three models and three datasets, for two tolerance thresholds ϵ= 1% (orange/red) and ϵ= 5% (blue). The baseline accuracy of the original uncompressed model is noted in parentheses. Since the performance of the Genetic Algorithm (GA)- based pruning is strictly supe... | https://arxiv.org/abs/2505.18350v1 |
70.5 35.0 Sentiment Analysis Sentiment-II 91.2 83.5As seen in Table 1, LLM- Sieve generalizes well across datasets in the same task domain for Gen RAG-II (no loss) and Sentiment-II ( ≈7% loss). However, performance drops significantly in Med RAG-II. We found that this stems from a mismatch in output format: Med RAG-I r... | https://arxiv.org/abs/2505.18350v1 |
8 270 LLaMA-3.1-70B 35 85 891Running LLM-Sieve incurs a one-time cost com- parable to LoRA fine-tuning. As shown in Ta- ble 2, pruning itself requires 1–36 GPU hours depending on the model. The search for pruning factors is more expensive, as it resembles hyper- parameter tuning and involves multiple pruning iterations... | https://arxiv.org/abs/2505.18350v1 |
Linguistics and the 10th International Joint Conference on Natural Language Processing , pages 884–889, 2020. [11] Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323 , 2022. [12] Guangxuan X... | https://arxiv.org/abs/2505.18350v1 |
assess the impact of calibration dataset size, we ran a sensitivity analysis on Phi-3-mini for all our tasks using LLM-Sieve configured with uniform pruning. As seen in Fig. 13, we observe that accuracy plateaus after approximately 150K tokens. Based on this, we use a fixed calibration set of 200K tokens for all our pr... | https://arxiv.org/abs/2505.18350v1 |
higher compression). 13 A.4 Presence of Bottleneck Matrices. We perform a cross-population analysis of the top-performing individuals—defined as those within 20% of the best recorded fitness—during our genetic algorithm search. For each matrix in every layer, we compute the probability that it remains unpruned (i.e., r... | https://arxiv.org/abs/2505.18350v1 |
arXiv:2505.18356v1 [cs.CL] 23 May 2025The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs Lucas Bandarkar* Nanyun Peng University of California, Los Angeles Abstract Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate c... | https://arxiv.org/abs/2505.18356v1 |
et al., 2024). This no- tably contrasts mathematical reasoning capabilities being encoded mainly in the middle transformer layers (Hanna et al., 2023; Stolfo et al., 2023). In the context of cross-lingual transfer, this functional separation motivates modular approaches to fine- tuning, which distinct model components ... | https://arxiv.org/abs/2505.18356v1 |
capabilities. Amongst our modular solutions, we surpris- ingly find that post hoc model merging via Layer- Swapping outperforms more coordinated multi- task fine-tuning approaches. To contextualize this counterintuitive result, we explore recent academic literature that help explain the phenomenon. We provide empirical... | https://arxiv.org/abs/2505.18356v1 |
mod- ular parameters were developed to compose capa- bilities for transfer learning by inserting trainable adapters within model layers (Houlsby et al., 2019; Pfeiffer et al., 2021). These methods were modi- fied for multilinguality by allocating adapters for particular languages and switching them in or outdepending o... | https://arxiv.org/abs/2505.18356v1 |
display exact-match (EM) accuracy ( ↑) as a percentage. 3 Experimental Setup 3.1 Evaluation Limited by the lack of task-specific benchmarks for medium- and low-resource languages, we focus on MGSM (Shi et al., 2023) as the target task of this project. MGSM is a mathematical reasoning benchmark parallel across 10 langua... | https://arxiv.org/abs/2505.18356v1 |
when freez- ing parameters is because the trainable parameters are particularly useful for a target task, we also run experiments with the opposite allocation (e.g. mid- dle layers frozen during mathematical reasoning training) and find that it works poorly. 4 Parameters that are frozen or resetFrozen duringReset after... | https://arxiv.org/abs/2505.18356v1 |
LoRA were minor unless noted other- wise. With four models, three languages, and two fine-tuning approaches (full and LoRA), we have a total of 24 experimental settings. For each, we do hyperparameter search over several runs to ensure comparability (See Appendix A.4 for details). 4 Experiments We describe numerous met... | https://arxiv.org/abs/2505.18356v1 |
This frequent back-and-forth is intended to ensure the coordination of parameter updates during multi- task optimization. The validation set contains an equal amount from each datasets.Switching We default to a single step before switching to best simulate fully simultaneous train- ing, but additionally experiment with... | https://arxiv.org/abs/2505.18356v1 |
datasets. discussed in Sections 4.1 to 4.5. Despite the small magnitude of differences, the rank-based Friedman test (non-parameteric) shows statistically signifi- cant differences between the treatments at the 0.05 significance level. In our setting, we find that only training on the language dataset is more effective... | https://arxiv.org/abs/2505.18356v1 |
MGSM in the target language. This is notable because MGSM in the target lan- guage is the target task of course, yet results more directly related to the training data tends to be more important for proper task composition. 7 6 Discussion Given the rejection of our hypothesis that simulta- neous fine-tuning would most ... | https://arxiv.org/abs/2505.18356v1 |
methods that fine-tune task and language together or do not ad hoc revert param- eter updates. We conjecture that the success of this ad hoc merging method is because the math and language experts, when represented as task vectors, exhibit a high degree of linearity. As a re- sult, this method benefits from more robust... | https://arxiv.org/abs/2505.18356v1 |
Annual Meeting of the Association for Computational Lin- guistics (Volume 1: Long Papers) , pages 1778–1796, Dublin, Ireland. Association for Computational Lin- guistics.Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018. Unsupervised neural ma- chine translation. In International Conference on Learning... | https://arxiv.org/abs/2505.18356v1 |
In International Conference on Learn- ing Representations . Rui Dai, Sile Hu, Xu Shen, Yonggang Zhang, Xinmei Tian, and Jieping Ye. 2025. Leveraging submodule linearity enhances task arithmetic performance in LLMs. In The Thirteenth International Conference on Learning Representations . John Dang, Arash Ahmadian, Kelly... | https://arxiv.org/abs/2505.18356v1 |
learning for NLP. In Proceedings of the 36th International Conference on Machine Learning , volume 97 of Proceedings of Machine Learning Research , pages 2790–2799. PMLR. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of lar... | https://arxiv.org/abs/2505.18356v1 |
Benchmarks Track . Team Llama, Abhimanyu Dubey, Abhinav Jauhri, Abhi- nav Pandey, Abhishek Kadian andAhmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and et al. 2024. The llama 3 herd of models. Meta Research . Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularizatio... | https://arxiv.org/abs/2505.18356v1 |
Ivan Vuli ´c, Iryna Gurevych, and Se- bastian Ruder. 2020. MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer. InProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages 7654–7673, Online. Association for Computa- tional Linguistics. Fred Philippy, Siwe... | https://arxiv.org/abs/2505.18356v1 |
tiarachchi, Joseph Wilson, Marina Machado, Luisa Moura, Dominik Krzemi ´nski, Hakimeh Fadaei, Irem Ergun, Ifeoma Okoh, and 14 others. 2024. Aya dataset: An open-access collection for multilingual instruction tuning. In Proceedings of the 62nd An- nual Meeting of the Association for Computational Linguistics (Volume 1: ... | https://arxiv.org/abs/2505.18356v1 |
Information Process- ing Systems . An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jian- hong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, and 22 oth- ers. 2024. Qwen2.5 technical report. ... | https://arxiv.org/abs/2505.18356v1 |
0-1% lower than LoRA results. A.2 CPT Results for Q WEN2.5 in Bengali Detailed Performance of CPT Experiments SFT Dataset None Mix Math-Only Lang-Only Simult. Layer-Swapping SFT Type Base Full Full Part.FT Full Part.FT Part.FT Full Part.FT Bengali 37.6% 38.2% 33.2% 34.2% 37.6% 37.8% 38.8% 39.4% 38.8% English 76.8% 77.6... | https://arxiv.org/abs/2505.18356v1 |
averaged across four models. We see that while math-only SFT (green) does well for Swahili and mixed-data SFT (red) does well for Bengali, our two modular solutions work consistently well across the three languages. Note: the y-axis is a percentage because the evaluation score is accuracy, notbecause this table display... | https://arxiv.org/abs/2505.18356v1 |
arXiv:2505.18363v1 [cs.CL] 23 May 2025SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases AmirHossein Safdarian1, Milad Mohammadi1, Ehsan Jahanbakhsh1, Mona Shahamat Naderi2,Heshaam Faili1 1University of Tehran, Iran2Sharif University of Technology, Iran {... | https://arxiv.org/abs/2505.18363v1 |
capture semantic signals beyond surface overlap, but typically require supervised training, complex multi-stage pipelines, or brittle prompt engineering. They also struggle with the core trade-off: being precise enough to reduce noise, yet broad enough not to miss critical context (Liu et al., 2024; Wang et al., 2025).... | https://arxiv.org/abs/2505.18363v1 |
model’s ability to focus on relevant elements. 2.1 Schema Linking in Text-to-SQL Schema linking—the process of aligning natural language mentions to corresponding tables and columns in a database—is a crucial component of Text-to-SQL systems (Lei et al., 2020; Liu et al., 2022; Li et al., 2023c). Early approaches relie... | https://arxiv.org/abs/2505.18363v1 |
model. Interactive- T2S (Xiong et al., 2024) equips an LLM agent with a FINDSHORTEST PATH tool that runs breadth- first search over the foreign-key graph to supply valid join chains during multi-turn dialogue. These works demonstrate the practicality of DFS/BFS as auxiliary helpers, but the graph search remains pe- rip... | https://arxiv.org/abs/2505.18363v1 |
and output. We operationalize schema linking as a path- selection task on the schema graph G, which en- ables systematic and efficient sub-schema identifi- cation: This extraction is performed via a single call to Gemini 2.5 Flash, guided by a dedicated system prompt designed to elicit precise identification of source ... | https://arxiv.org/abs/2505.18363v1 |
on the BIRD de- velopment split, which comprises 1,534 natural- language questions over 11 heterogeneous rela- tional databases. For schema linking precision, recall, and exact match rate, we use the BIRD dev set gold queries by extracting the referenced ta- bles. For execution accuracy, we follow the official evaluati... | https://arxiv.org/abs/2505.18363v1 |
far more damaging than includ- ing extras (Glass et al., 2025). By pushing both recall and F 6to new highs without any supervised training, SchemaGraphSQL force-union establishes a new performance bar for zero-shot schema link- ing. Table 1: Schema Linking Results in Dev Mode Method Exact Match Rate (%) Precision (%) R... | https://arxiv.org/abs/2505.18363v1 |
is far more damaging than including extras—LLMs can ignore noise but cannot guess missing joins. Among schema metrics, F 6correlates best with Table 3: SQL Execution Accuracy Results - Dev LLM Method Simple (%) Moderate (%) Challenging (%) Total (%) Gemma-3-4BIdeal Schema Linking 42.49 21.94 16.67 33.83 Baseline 30.05 ... | https://arxiv.org/abs/2505.18363v1 |
Xiang Bai. 2024. Rsl- sql: Robust schema linking in text-to-sql generation. Preprint , arXiv:2411.00073. Zhi Chen, Lu Chen, Yanbin Zhao, Ruisheng Cao, Zihan Xu, Su Zhu, and Kai Yu. 2021. ShadowGNN: Graph projection neural network for text-to-SQL parser. In Proceedings of the 2021 Conference of the North American Chapte... | https://arxiv.org/abs/2505.18363v1 |
Association for Computational Lin- guistics , pages 7567–7578, Online. Association for Computational Linguistics. Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xian- pei Han, Le Sun, Hao Wang, and Zhenyu Zeng. 2025. Dbcopilot: Natural language querying over massive databases via schema routing. Preprint , arXiv:2312.03463. ... | https://arxiv.org/abs/2505.18363v1 |
query that answers a user’s question using the provided schema. INPUTS •Schema: {schema} •Question Context: {evidence_string} INSTRUCTIONS 1.Generate a correct SQLite query that answers the user question. 2.Ensure the query is syntactically valid and aligns with the schema. 3. Format the query clearly and cleanly. B Ad... | https://arxiv.org/abs/2505.18363v1 |
arXiv:2505.18366v1 [cs.IR] 23 May 2025Accepted in ACL 2025 Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems Hansa Meghwani*, Amit Agarwal*, Priyaranjan Pattnayak, Hitesh Laxmichand Patel ,Srikant Panda Oracle AI Correspondence: hansa.meghwani@oracle.com; amit.h.agarwal@oracle.com* Abstract Enter... | https://arxiv.org/abs/2505.18366v1 |
significant improvements across both proprietary and publicly available datasets, verifying our method’s impact and broad applicability across domain-specific usecases. 3.In-depth analysis, of critical challenges in han- dling both short and long-form enterprise doc- uments, laying a clear foundation for targeted futur... | https://arxiv.org/abs/2505.18366v1 |
structured, modular framework that integrates diverse embedding models, dimen- sionality reduction, and a novel semantic criterion for hard-negative selection. Figure 1 illustrates the high-level pipeline, components and their interac- tions. The re-ranking models fine-tuned using the Accepted in ACL 2025 Figure 1: Ove... | https://arxiv.org/abs/2505.18366v1 |
x. 3.3 Dimensionality Reduction To alleviate the computational overhead arising from high-dimensional concatenated embeddings, we apply PCA to reduce dimensionality while pre- serving semantic richness: XPCA=XconcatP, (3) where Prepresents the PCA projection matrix. We specifically select PCA due to its computational e... | https://arxiv.org/abs/2505.18366v1 |
ADORE+STAR 0.54 0.57 0.52 0.54 0.48 0.52 0.63 0.66 Our Proposed HN 0.57 0.64 0.54 0.56 0.52 0.55 0.65 0.69 Table 2: Comparative performance benchmarking of our in-house reranker across multiple domain-specific datasets. The reranker is fine-tuned (FT) with different negative sampling techniques, highlighting the effect... | https://arxiv.org/abs/2505.18366v1 |
in ACL 2025 sampling method is not only effective within our internal enterprise corpus but also valuable across diverse, domain-specific public datasets, indicating broad applicability and domain independence. Model MRR@3 MRR@10 Short DocumentsBaseline 0.481 0.526 FT w/ proposed HN 0.61 0.662 Long DocumentsBaseline 0.... | https://arxiv.org/abs/2505.18366v1 |
but contextually irrelevant documents. Figure 3: Illustrations of similar topics in the domain of Cloud Computing Case Study 1: Disambiguating Technical Acronyms. •Query (Q): "What is VCN in Cloud Infras- tructure?" Accepted in ACL 2025 •Positive Document (PD): A document ex- plaining "Virtual Cloud Network (VCN)" in C... | https://arxiv.org/abs/2505.18366v1 |
analysis of their structural complexity. Our current use of embed- ding concatenation for ensembling could also be refined—future work should evaluate alternative fusion techniques such as weighted averaging or attention-based mechanisms. Moreover, extending the retrieval framework to support cross-lingual and multilin... | https://arxiv.org/abs/2505.18366v1 |
evaluation, and detection. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasu- pat, and Ming-Wei Chang. 2020. Realm: Retrieval- augmented language model pre-training. EK Jasila, N Saleena, and KA Abdul Nazeer. 2023. An efficient document clustering approach for devising semantic clusters. Cybernetics andSystems , pages 1... | https://arxiv.org/abs/2505.18366v1 |
Kumar, Srikant Panda, Priyaranjan Pat- tnayak, Taki Hasan Rafi, Tejaswini Kumar, and Dong- Kyu Chae. 2025. Sweeval: Do llms really swear? a safety benchmark for testing limits for enterprise use. In Proceedings ofthe2025 Conference ofthe Nations oftheAmericas Chapter oftheAssociation forComputational Linguistics: Human... | https://arxiv.org/abs/2505.18366v1 |
trieval. Zhen Yang, Zhou Shao, Yuxiao Dong, and Jie Tang. 2024. Trisampler: A better negative sampling princi- ple for dense retrieval. Preprint, arXiv:2402.11855. Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. Optimizing dense retrieval model training with hard negatives. SIGIR 202... | https://arxiv.org/abs/2505.18366v1 |
these techniques to dynamically identify negatives that challenge retrieval models in a scalable manner. Synthetic Data in Retrieval Recent work (Askari et al., 2023; Agarwal et al., 2024a,b; Patel et al., 2024; Dua et al., 2024; Pabolu et al., 2024a,b) has explored using large language models to generate synthetic tra... | https://arxiv.org/abs/2505.18366v1 |
reranker training. A.2.3 Unified Contrastive Loss The unified contrastive loss is designed to improve ranking precision for both bi-encoders and cross- encoders, by ensuring that positive documents (PD) are ranked closer to the query ( Q) than hard negatives ( DHN) by a margin m. The loss is de- fined as: L=NX i=1max (... | https://arxiv.org/abs/2505.18366v1 |
10 ranked documents. Our method shows promising results even with smaller training sets, demonstrating the effective- ness of incorporating hard negatives early in the training process. This suggests that hard negatives significantly enhance the model’s ability to distin- guish relevant from irrelevant documents agains... | https://arxiv.org/abs/2505.18366v1 |
arXiv:2505.18374v1 [cs.CL] 23 May 2025ShIOEnv: A CLI Behavior-Capturing Environment Enabling Grammar-Guided Command Synthesis for Dataset Curation Jarrod Ragsdale The University of Texas at San Antonio One UTSA Circle, San Antonio, TX, USA jarrod.ragsdale@utsa.eduRajendra Boppana The University of Texas at San Antonio ... | https://arxiv.org/abs/2505.18374v1 |
such a dataset requires enumerating a command’s arguments to find novel combinations that demonstrate each possible behavior for that command. A naive exhaustive enumeration of command–argument combinations without considering syntactic validity is inefficient, as a substantial subset of combinations will be syntactica... | https://arxiv.org/abs/2505.18374v1 |
of data. CLI Datasets Existing CLI command datasets such as NL2BASH [6] and NL2CMD [7] present natural-language (NL) descriptions paired with commands for transductive tasks. Because these corpora treat the CLI as a textual target rather than an executable program, they neglect to provide 2 Table 1: Terminal command da... | https://arxiv.org/abs/2505.18374v1 |
reward that measures the behavioural minimality of each argument sequence, eliminating the need for pre-existing unit tests or oracle outputs. Syntax -Constrained Generation for Efficient Exploration A CFG is a formal definition of a language structure where a start token is expanded using production rules that repeate... | https://arxiv.org/abs/2505.18374v1 |
actions not masked to a large negative value, negating their probability, 4 3.3 Reward Formulation yielding the production-masked conditional policy πn: πn(a|st) =x(n, a)π(a|st)P a′′∈Aax(n, a′′)π(a′′|st). The renormalized distribution confines exploration to syntactically valid actions, raising the baseline for combina... | https://arxiv.org/abs/2505.18374v1 |
onwards. rd tandrc tcan be applied to a per-step reward to inform redundancy changes with each argument addition by measuring changes in rd torrc t, providing feedback for each new argument. An increase in these signals indicates that the argument contributes meaningfully to the final behavior, while decreased signals ... | https://arxiv.org/abs/2505.18374v1 |
agent incrementally constructs command sequences from a start state of a starting directory by sampling productions until all non-terminals are resolved or an arbitrarily chosen 14-argument horizon is met (steps 1-2). Generated sequences are evaluated through behavioral comparison with argument-omitted 6 4.2 Objective ... | https://arxiv.org/abs/2505.18374v1 |
OP is evident, with GCPN-m0 and GCPN-m50 surpassing their random analogues within 3K episodes and UCPN-m50 overtaking UCRT after roughly 7K episodes. Interestingly, the margin penalty of 0.5 improves earlier and elevates asymptotic performance, with GCPN-m50 approaching 0.7 OP and converging near 0.6 by 5K episodes, co... | https://arxiv.org/abs/2505.18374v1 |
all other data generation methods with a character F1 score of 75.63 and BLEU-4 score of 0.618 and, 11% higher than the closest other dataset (GCPN-m0) and 26% higher than the random baseline (GCRT). These gains demonstrate that signals provided by the environment provide meaningful guidance for command synthesis and t... | https://arxiv.org/abs/2505.18374v1 |
misaligning returns from temporal differences. A hierarchical action-selection framework might address these issues, which we leave for future work. Nevertheless, this work establishes an extendable and modifiable environment for synthesizing CLI command sequences, supporting future, more extensive studies. 6 Conclusio... | https://arxiv.org/abs/2505.18374v1 |
proceedings . neurips . cc / paper _ files / paper / 2023 / hash / 4b175d846fb008d540d233c188379ff9-Abstract-Datasets_and_Benchmarks.html . [10] Zishun Yu et al. “ B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis”. In: arXiv:2310.03173 (Mar. 2024). arXiv:2310.03173 [cs]. DOI:10.48550/arXiv.2310. 0... | https://arxiv.org/abs/2505.18374v1 |
arXiv preprint arXiv:1707.06347 (2017). [33] Kishore Papineni et al. “Bleu: a method for automatic evaluation of machine translation”. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics . 2002, pp. 311–318. [34] Maja Popovi ´c. “chrF: character n-gram F-score for automatic MT ev... | https://arxiv.org/abs/2505.18374v1 |
context_key String Key detailing environment change, if any, from executing the input context_value String Observed change in context when the input is executed Figure 4: Adapted NL2bash dataset metadata are omitted. Each dataset covers 40 utilities distributed according to the generating policy. We exclude repeatedly ... | https://arxiv.org/abs/2505.18374v1 |
so the tensor maintains a fixed shape. At reset, the first row is pre -initialised with (cd, c0) where c0is a starting directory drawn uniformly from a user -defined set. Two internal counters (h, l)track the agent’s position inside the tensor. The truncate flag is returned when either counter reaches its bound. B.1.2 ... | https://arxiv.org/abs/2505.18374v1 |
(in our evaluation, the first argument is always a given command). An indicator is added to provide a maximum reward for cases where r∆ t= 0 with a perfect uniqueness score, providing a strong signal for reinforcement of maintaining objective completion. This intermediate reward is scaled by a factor δ: [0,1]to reduce ... | https://arxiv.org/abs/2505.18374v1 |
arXiv:2505.18383v1 [cs.CL] 23 May 2025 NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities Abdellah El MekkiλHoudaifa AtouδOmer Nacarψ Shady Shehataξ,γMuhammad Abdul-Mageedλ,ξ,γ λThe University of British ColumbiaδUM6PψPSU ξMBZUAIγInvertible AI {abdellah.elmekki,muhammad.mageed}@ubc... | https://arxiv.org/abs/2505.18383v1 |
K oshary is truly a poor man's meal, isn't i t? Mostafa: Isn't it though? B ut I worry about i t a bit. They sa y leftover rice can cause f ood poisoning. Ahmed: Don't worry , man, this place is clean. And our Alexandrian koshary is something else; the y ellow lenti ls without sauce ar e a whole di fferent taste. Mosta... | https://arxiv.org/abs/2505.18383v1 |
languages spoken in regions with high economic influence (Bender, 2011; Joshi et al., 2020). Beyond linguistic limitations, a more profound challenge is the inherent risk of cultural encapsu- lation (Wrenn, 1962) in LLMs. Cultural encapsu- lation refers to an unconscious tendency to oper- ate within one’s own cultural ... | https://arxiv.org/abs/2505.18383v1 |
and alignment with cultural knowledge and values. Our findings show that the adapted model significantly outperforms baseline and existing models that are even bigger in size on most evaluation tasks. The main contributions of this work are: (i)A novel framework for augmenting pre-training cor- pora tailored to local c... | https://arxiv.org/abs/2505.18383v1 |
three primary dimensions (Geertz, 1977; Ander- son, 1991; Bourdieu and Thompson, 1991; Higgins and Douglas, 2020; Stanlaw and Adachi, 2025): (i) Language: Encompassing dialectal nuances, idiomatic expressions, and linguistic structuresunique to the community. (ii) Cultural Heritage: Reflecting the customs, traditions, ... | https://arxiv.org/abs/2505.18383v1 |
proverbs, idioms, dia- logues from TV programs, and local terminology, pairing each with English translations for accuracy. Representative Personas. We develop represen- tative personas reflecting local moral, demographic, and socioeconomic attributes by leveraging data from the World Values Survey (WVS) (EVS/WVS, 2024... | https://arxiv.org/abs/2505.18383v1 |
corpus comprising approxi- mately 1.5 million Egyptian and 800,000 Moroccan news articles, originally published in MSA by local news websites. Additionally, we include 25,000 Egyptian and 49,000 Moroccan Wikipedia articles. Fordialectal glosses, expressions, and utterances , we draw from publicly available resources on... | https://arxiv.org/abs/2505.18383v1 |
Data. To adapt our pre-trained model for instruc- tion following, we perform supervised fine-tuning (SFT). Due to the scarcity of SFT datasets for EGY and MOR, we construct a comprehensive training set. This process involves several key steps: (i) translation of SmolTalk dataset (Allal et al., 2025) into MOR, EGY , Fre... | https://arxiv.org/abs/2505.18383v1 |
ground- truth answers on a scale from 0 to 10. The final evaluation score is calculated as the average cor- rectness across all responses. Translation. We evaluate the translation perfor- mance across multiple directions: dialect↔dialect (i.e., Moroccan ↔Egyptian), dialect↔MSA , English ↔dialect , and French↔dialect . ... | https://arxiv.org/abs/2505.18383v1 |
against an NLLB-200’s 3.3B variant (Team et al., 2022). 6 EGY and MOR when compared to similar size models. Specifically, NileChat surpasses its base- line model, Qwen2.5-3B-instruct, by a signifi- cant margin of ∼10 points across the majority of these tasks. Notably, NileChat also outperforms larger Arabic-focused mod... | https://arxiv.org/abs/2505.18383v1 |
12.34 26.50 18.39 21.32More than 7BAceGPT-7B-chat 18.02 11.33 21.11 17.46 14.73 4.95 20.10 7.47 14.40 ALLaM-7B-Instruct 23.91 15.88 24.74 23.19 19.98 9.16 29.40 18.51 20.60 Qwen2.5-7B-Instruct 14.41 10.23 19.81 18.95 10.43 4.10 20.92 8.80 13.46 Qwen3-8B 20.03 13.86 22.56 21.33 13.38 4.73 24.14 9.27 16.16 Atlas-Chat-9B ... | https://arxiv.org/abs/2505.18383v1 |
adapting LLMs to specific communities by deeply integrat- ing their unique linguistic characteristics, cultural heritage, and societal values. Our approach lever- ages a teacher model proficient in generating low- resource languages to enable: (i) translation for the incorporation of community-specific language and (ii... | https://arxiv.org/abs/2505.18383v1 |
this process is critically informed by ground-truth cultural values survey data from the communities of interest and local context to control the generation. This approach aims to imbue our models with specific cultural nuances relevant to these communities. As our evaluations demonstrate, the resulting models exhibit ... | https://arxiv.org/abs/2505.18383v1 |
1991. Imagined Communities: Re- flections on the Origin and Spread of Nationalism . Verso, London. Lucas Bandarkar, Davis Liang, Benjamin Muller, Mikel Artetxe, Satya Narayan Shukla, Donald Husa, Naman Goyal, Abhinandan Krishnan, Luke Zettlemoyer, and Madian Khabsa. 2024. The belebele benchmark: a parallel reading comp... | https://arxiv.org/abs/2505.18383v1 |
frontier. Preprint , arXiv:2412.04261. Ashutosh Dwivedi, Pradhyumna Lavania, and Ashutosh Modi. 2023. EtiCor: Corpus for analyzing LLMs for etiquettes. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Process- ing, pages 6921–6931, Singapore. Association for Computational Linguistics. Abde... | https://arxiv.org/abs/2505.18383v1 |
Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Juny- ing Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, and Jinchao Xu. 2024. AceGPT, localizing large language models in Arabic. In Proceedings of the 2024 Conference of the North American Chapter of t... | https://arxiv.org/abs/2505.18383v1 |
In Findings of the Associa- tion for Computational Linguistics: EMNLP 2023 , pages 1404–1422, Singapore. Association for Com- putational Linguistics. Tarek Naous, Michael J Ryan, Alan Ritter, and Wei Xu. 2024. Having beer after prayer? measuring cultural bias in large language models. In Proceedings of the 62nd Annual ... | https://arxiv.org/abs/2505.18383v1 |
Rada Mihalcea. 2024. Understanding the capabilities and limitations of large language models for cultural commonsense. InProceedings of the 2024 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages 5668–5680, Mexico City... | https://arxiv.org/abs/2505.18383v1 |
Gao, and Yanyong Zhang. 2025. Language adaptation of large language models: An empirical study on LLaMA2. In Proceedings of the 31st International Conference on Computational Linguistics , pages 7195–7208, Abu Dhabi, UAE. Association for Com- putational Linguistics. Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai... | https://arxiv.org/abs/2505.18383v1 |
details B.1 Pre-training Motivations for choosing Qwen-2.5-3B as our backbone model. We select Qwen-2.5-3B as our base model to continue pretrain for two primary reasons: its competitive performance on MSA tasks and good tokenizer compression ratio on Arabic dialect texts. At the time of the selection, the Gemma 2 (Tea... | https://arxiv.org/abs/2505.18383v1 |
was augmented with a shared multilingual corpus which included MSA data (e.g., MSA SmolTalk, and data from the ORCA and Dolphin datasets). It is plausible that EGY is linguistically closer to MSA compared to the MOR, which is often considered more distant from MSA due to influences such as Berber and French. Consequent... | https://arxiv.org/abs/2505.18383v1 |
text casual , conversational , and reflective of how Moroccans would naturally write in everyday situations using Arabizi . Translate only the content keys in the following JSON , and output a json of the same format : { JSON_OBJECT } Figure 6: The prompt used with our teacher LLM to convert dialectal Arabic text writt... | https://arxiv.org/abs/2505.18383v1 |
e v e l f l u e n c y i n Moroccan A r a b i c d i a l e c t w r i t t e n i n A r a b i c s c r i p t . Your t a s k i s t o t r a n s f o r m d e t a i l e d a r t i c l e s or i n f o r m a t i o n ( l i k e r e c i p e s , h i s t o r i c a l a c c o u n t s , c u l t u r a l t r a d i t i o n s , e t c . ) i n t o... | https://arxiv.org/abs/2505.18383v1 |
o r someone wanting t o l e a r n p r a c t i c a l i n f o r m a t i o n 4 . Output t h e r e s u l t s i n s t r u c t u r e d JSON f o r m a t ## I n s t r u c t i o n Format G u i d e l i n e s : − For p r o c e d u r a l c o n t e n t ( r e c i p e s , c r a f t s , e t c . ) : C r e a t e "how t o " q u e s t i o... | https://arxiv.org/abs/2505.18383v1 |
t o n e c o n v e r s a t i o n a l and h e l p f u l , as i f e x p l a i n i n g t o a f r i e n d ## Language G u i d e l i n e s : − Use a u t h e n t i c Moroccan A r a b i c d i a l e c t w r i t t e n i n A r a b i c s c r i p t ( n o t t r a n s l i t e r a t i o n ) − I n c l u d e t y p i c a l Moroccan cooki... | https://arxiv.org/abs/2505.18383v1 |
t h e r p r a c t i c a l i n s t r u c t i o n ] " , " r e s p o n s e " : " [ a n o t h e r d e t a i l e d r e s p o n s e ] " } ] } ``` ## I n s t r u c t i o n s : 1 . G e n e r a t e a t l e a s t 3−5 p r a c t i c a l i n s t r u c t i o n − r e s p o n s e p a i r s based on t h e c o n t e n t I p r o v i d e ... | https://arxiv.org/abs/2505.18383v1 |
s p o n s e s t o p r o v i d e d e p t h . 8 . I f t h e a r t i c l e does n o t have any r e l e v e n t i n f o r m a t i o n t o t h e Moroccan c u l t u r e t h e n r e t u r n an empty l i s t . Now, I ' l l p r o v i d e you w it h c o n t e n t , and you ' l l t r a n s f o r m i t i n t o p r a c t i c a l i ... | https://arxiv.org/abs/2505.18383v1 |
اﻟدﺟﺎج ﺑﺎﻟزﯾﺗون اﻟﻣﻐرﺑﻲ إﻧﺗﺷﺎرا واﺳﻌﺎ ﻓﻲ اﻟﺟزاﺋر، ﺧﺻوﺻﺎ ﺑﻣدﯾﻧﺔ ﺗﻠﻣﺳﺎن. و ﯾﻔﺳر ھذا اﻹﻗﺑﺎل ﺑﺎﻧﺟذاب ﻋﺷﺎق اﻟطﺎﺟﯾن اﻟﻣﻐرﺑﻲ إﻟﻰ ﺟﻐراﻓﯾﺎ اﻟﻣدﯾﻧﺔ اﻟﻘرﯾﺑﺔ ﻣن اﻟﻣﻐرب. طﻘوس ﻣرﺗﺑطﺔ. اﻟﺷﻼل. ﯾﺗم ﺗﻘدﯾم ھذا اﻟطﺑق ﺑﻌد ﻏﺳﯾل اﻷﯾﺎدي ﻋﻠﻰ اﻟطرﯾﻘﺔ اﻟﻣﻐرﺑﯾﺔ اﻷﺻﻠﯾﺔ ﺑﺎﺳﺗﺧدام ﻣﺎ ﯾﺳﻣﻰ ﺑﺎﻟﺷﻼل اﻟﻣﻐرﺑﻲ اﻟذي ﯾﻌﺗﺑر ﻣن طﻘوس اﻟﺿﯾﺎﻓﺔ اﻟﻣﻐرﺑﯾﺔ و ھو ﻋﺑﺎرة ... | https://arxiv.org/abs/2505.18383v1 |
business or industry. He is in the third income decile and considers himself lower class. He has spent savings and borrowed money, and rates his financial satisfaction as 2 out of 10 and his overall life satisfaction as 3 out of 10. Despite this, he reports good health and rates his control over life as 5 out of 10. Ha... | https://arxiv.org/abs/2505.18383v1 |
إﻣﺎ ﺑﺎﻷرز. واﻟﻠﻲ ﺑﯾﺣﺑوا اﻟﺑرﻏل ﺑﯾﻌﻣﻠوه ﻣﻊ اﻟﻌدس اﻷﺳود اﻟﻣﺳﻠوق وﺑﯾﻘدﻣوه ﺳﺎﺧن أو ﺑﺎرد، ﺧﺻوﺻﺎً ﻟو ﺣطوا ﻋﻠﯾﮫ زﯾت زﯾﺗون ﺑدل اﻟﺳﻣﻧﺔ. وﻓﻲ اﻟﻌراق، اﻟﻛﺷري ﺑﯾﺗﺣﺿر ﺑﺎﻷرز واﻟﻌدس اﻷﺻﻔر اﻟﻣﺟروش، وﺑﯾﻘدﻣوه ﻣﻊ ﻛﺑﺔ اﻟﺣﺎﻣض. ﺑس ﺧدوا ﺑﺎﻟﻛم، ﻓﻲ ﺑﻌض اﻟﺗﺣذﯾرات ﻣن أﻛل اﻟﻛﺷري اﻟﻠﻲ ﻓﯾﮫ أرز ﻣﻌﺎد ﺗﺳﺧﯾﻧﮫ، ﻷن ده ﻣﻣﻛن ﯾﺳﺑب ﻧوع ﻣن اﻟﺑﻛﺗﯾرﯾﺎ اﻟﻠﻲ ﻣﻣﻛن ... | https://arxiv.org/abs/2505.18383v1 |
ﻛﺗﻌﺎﻧﻲ ﺷوﯾﺔ ﻣن ھﺎد اﻟﻣﺷﻛل. - آه ﻓﮭﻣت، ﯾﻌﻧﻲ ﻛﺎﯾﻧﺔ ﺷﻲ ﻣﺷﺎﻛل دﯾﺎل اﻟﺻرف اﻟﺻﺣﻲ ﻓطﻣﺎرﯾس؟ - ﺑﺎﻟﺿﺑط، ﻛﺎﯾن ﺷﻲ ﻣﺷﺎﻛل ﻣﺧﺑﯾﯾن، وﻛﺎﯾن ﺷﻲ ﻣﻧﺎطق ﻛﯾﺗﺟﻣﻊ ﻓﯾﮭﺎ ﻣﯾﺎه اﻷﻣطﺎر وﻛﯾﺗﺳرﺑو ﻟﻠﻣﯾﺎه اﻟﻌﺎدﻣﺔ، وﻛﺎﯾﻧﺔ ﺷﻲ ﻣﺷﺎﻛل دﯾﺎل اﻟﺗﻠوث. - ﻣﺳﺎﻛن، ﺧﺎﺻﮭم ﯾدﯾرو ﺷﻲ ﺣل، ﺣﯾت ھﺎدﺷﻲ ﻛﯾﺧﻠﻲ اﻟﻣﻧطﻘﺔ رﯾﺢ وﺑﻼ ﺑﻧﯾﺔ ﺗﺣﺗﯾﺔ ﻣزﯾﺎﻧﺔ. - ﺑﺎﻟﺿﺑط، ھﺎد اﻟﻣﺷروع ﻏﺎدي ﯾدﯾر ... | https://arxiv.org/abs/2505.18383v1 |
27.33 22.89 22.89 ar-stablelm-2-chat 39.54 38.32 34.33 33.40 24.22 22.78 Atlas-Chat-2B 42.65 45.06 29.62 34.78 54.67 59.00 Llama-3.2-3B-Instruct 31.10 30.92 28.86 28.39 49.67 40.89 gemma-3-4b-it 46.32 46.60 34.26 32.53 61.44 52.11 Qwen3-4B 28.59 28.52 30.21 29.53 22.89 22.89 Qwen2.5-3B-Instruct 35.71 37.67 31.17 29.62 ... | https://arxiv.org/abs/2505.18383v1 |
15.22 15.73 34.83 35.45 NileChat 23.81 22.68 40.25 39.25 28.81 29.50 52.98 53.43 24.05 23.49 46.30 45.56 20.90 20.51 38.22 37.64 30.58 31.90 54.53 56.19 15.15 17.90 30.76 36.00 23.39 25.03 40.37 41.94 13.18 14.91 29.61 32.52 22.49 23.24 41.63 42.82More than 7BAceGPT-7B-chat 19.92 18.93 36.91 35.72 17.67 20.04 44.09 45.... | https://arxiv.org/abs/2505.18383v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.