text string | source string |
|---|---|
long-context tasks improves and degrades, with the best performance observed when n= 10 . We hypothesize that this trend is due to an excessive number of documents increasing the task difficulty beyond the model’s learning capacity, thereby leading to a drop in performance. 4.2 Impact of Different Mixing Strategy To in... | https://arxiv.org/abs/2505.17134v1 |
Visualizations of LongMagpie characteristics: (a,b) t-SNE visualizations of query embed- dings from different datasets showing LongMagpie’s dispersed distribution indicating diversity; (c) Long-context performance vs. token consumption showing LongMagpie’s superior performance. and shows similar performance on ShortA V... | https://arxiv.org/abs/2505.17134v1 |
(Bai et al., 2024a) employs Self-Instruct with packing strategies but requires curated examples, ChatQA (Liu et al., 2024b) blends QA datasets with conversational QA, ChatQA 2 (Xu et al., 2024b) packs documents into 32-128K token contexts, LOGO (Tang et al., 2024) adapts self-synthesis for long- context alignment, and ... | https://arxiv.org/abs/2505.17134v1 |
Dong, Jie Tang, and Juanzi Li. Longbench v2: Towards deeper understanding and reasoning on realistic long-context multitasks. arXiv preprint arXiv:2412.15204 , 2024b. Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade, VageeshD C, Arun Iyer, Suresh Parthasarathy, Sriram Rajamani, B. Ashok, and Shashank Shet. Codeplan: Re... | https://arxiv.org/abs/2505.17134v1 |
Wang, Wenhan Wang, Yun Bai, Eric P Xing, Xiang Ren, and Fan Yang. Lm- infinite: Simple on-the-fly length generalization for large language models. arXiv preprint arXiv:2308.16137 , 2023. Or Honovich, Thomas Scialom, Omer Levy, and Timo Schick. Unnatural instructions: Tuning language models with (almost) no human labor.... | https://arxiv.org/abs/2505.17134v1 |
Kruszewski, Angeliki Lazaridou, Quan Ngoc Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fernández. The lambada dataset: Word prediction requiring a broad discourse context. arXiv preprint arXiv:1606.06031 , 2016. Bowen Peng, Ye Zheng, Tie Xiao, Guangtao Liu, Siyuan Wang, Yutao Yang, ... | https://arxiv.org/abs/2505.17134v1 |
instructions. arXiv preprint arXiv:2212.10560 , 2022b. URL https://arxiv.org/abs/2212.10560 . Yunshu Wu, Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, and Estevam Hruschka. Less is more for long document summary evaluation by llms. arXiv preprint arXiv:2309.07382 , 2023. Guangxuan Xiao, Han Tian, Ji Lin, Xiang Zhang, ... | https://arxiv.org/abs/2505.17134v1 |
2025b. 14 A Detailed Experimental Results A.1 Training Config We employ the AdamW (Loshchilov and Hutter, 2017) optimizer with parameters β1= 0.9and β2= 0.95. Following ProLong (Gao et al., 2024b), we concatenate samples up to 64K sequence length and apply the document masking technique to prevent interactions between ... | https://arxiv.org/abs/2505.17134v1 |
When can isotropy help adapt LLMs’ next word prediction to numerical domains? Rashed Shelim Department of Electrical and Computer Engineering & Department of Computer Science Virginia Tech rasheds@vt.eduShengzhe Xu Department of Computer Science Virginia Tech shengzx@vt.edu Walid Saad Department of Electrical and Compu... | https://arxiv.org/abs/2505.17135v2 |
nonlinear interactions between many parameters. This makes it difficult to understand how models arrive at their predictions and makes it challenging for users to trust the model outputs. LLMs’ tendency to hallucinate can have serious consequences in critical numeric applications. For example, prediction errors in frau... | https://arxiv.org/abs/2505.17135v2 |
domain can be modeled by time series forecast- ingtechniques Jin et al. [2024], Ansari et al. [2024] which are widely adopted in the machine learning literature. Formally, given a time series x1:T+L= [x1, . . . , x T, . . . , x T+L], where the first Ttime instances give the historical context, the next Ltime instances ... | https://arxiv.org/abs/2505.17135v2 |
to 1. Then, the normalized ground-truth model ∀i∈Vis given by p(kTl+1=i|k1:Tl) =exp(⟨ψ∗(k1:Tl), ψ∗(ki)⟩) P|V| i=1exp(⟨ψ∗(k1:Tl), ψ∗(ki)⟩)=exp(z∗ i(k, l)) Z∗(k, l) Since we do not know the ground-truth model in reality, we do not have access to the ground- truth model ψ∗(ki)andψ∗(k1:Tl). Instead, we only have access to ... | https://arxiv.org/abs/2505.17135v2 |
on unseen data, good performance during training does not necessarily provide any performance guarantee for the numeric downstream task on unseen scenarios. This can be formalized in the following theorem and the proof is provided in Appendix A. Theorem 3.1. Let the logits of the ground-truth model be bounded. Then for... | https://arxiv.org/abs/2505.17135v2 |
call these two datasets as “Dataset 1” and “Dataset 2”. The downstream task here is to predict the transport signalling property over wireless channel using LLM, where Dataset 1causes good down- stream performance (i.e., near optimal signal prediction), while the Dataset 2causes bad downstream task performance (i.e., h... | https://arxiv.org/abs/2505.17135v2 |
Appendix B for completeness. Lemma 4.1. Consider the Jacobian matrix J=h ∂gi(Ψ) ∂ψji|V| i,j=1, which represents the gradient of the self-attention mapping G(Ψ)with respect to the input time series token embeddings. Then the spectral norm of Jsatisfies ∥J∥2≤ |Λ|2P|V| i=1 pi,i+1 2 ψi−P|V| j=1pi,jψj 2 + ∆, where the 5 r... | https://arxiv.org/abs/2505.17135v2 |
investigation rather than a global estimate. We start by performing clustering on the LLM representations in the contextual embedding space. There are various methods for performing clustering, such as k-means, DBSCAN Ester et al. [1996]. We select K-means clustering method because it is reasonably fast in high embeddi... | https://arxiv.org/abs/2505.17135v2 |
the isotropy in GPT2 embedding space. From Figure 4b, we can see that the GPT2 has consistent near-zero cosine similarity values for all layers, including layer 6. This indicates that nearly perfect isotropy exists in the GPT2 embedding space for the Dataset 1, which preserves the structure in the GPT2’s hidden represe... | https://arxiv.org/abs/2505.17135v2 |
Seasonality kernel (period = 0.25H) Trend RationalQuadratic kernel ( α= 1) RationalQuadratic kernel ( α= 10 ) Non-Linear RBF kernel (length scale = 0.1) RBF kernel (length scale = 1) Stochastic WhiteKernel (noise level = 0.1) WhiteKernel (noise level = 1) Datasets. We conduct a comprehensive evaluation using 12differen... | https://arxiv.org/abs/2505.17135v2 |
the input data. The first scenario is important as it provides an analysis on selecting proper input context length rather than selecting the length through random trials and errors. The second scenario is important as it gives us ideas on how the level of noise in noisy data impacts performance, since the data in the ... | https://arxiv.org/abs/2505.17135v2 |
the noise in real time and take the necessary steps to clean the input time series for better performance. However, it is always possible to measure the isotropy from LLM hidden representations, which can be used as a measure of noise in the input datasets, and thus, help to improve the forecasting performance. 5.2 Qua... | https://arxiv.org/abs/2505.17135v2 |
per- formance when structure is not preserved in the LLM representations is a topic of future work. 11 References Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Syndar Rangapuram, Sebastian Pineda Arango, Shubham Kapoor, Jasper Zschiegner, and Maddix... | https://arxiv.org/abs/2505.17135v2 |
models are unsupervised multitask learners. 2019. Kashif Rasul, Arjun Ashok, Andrew Robert Williams, Hena Ghonia, Rishika Bhagwatkar, Arian Khorasani, Mohammad Javad Darvishi Bayazi, George Adamopoulos, Roland Riachi, Nadhir Hassen, Marin Biloš, Sahil Garg, Anderson Schneider, Nicolas Chapados, Alexandre Drouin, Valent... | https://arxiv.org/abs/2505.17135v2 |
variable ψjis expressed asJi,j=∂gi(Ψ) ∂ψj=pi,jI+Ψ⊤Qi ΨΛδi,j+Ej,iΨΛ⊤ where the matrix Qiis defined by Qi=diag(pi,:)−pi,:p⊤ i,:. Here, pi,:∈R|V| +corresponds to the i-th row of the probability matrix P, Ej,i∈R|V|×|V|denotes a matrix with a single entry at the (j, i)-th position and zeros elsewhere, and δi,j∈ {0,1}is th... | https://arxiv.org/abs/2505.17135v2 |
performing K-means clustering, each observation p(i.e., one of the Jvector representations in V) is assigned to one of Cclusters. For an observation passigned to the cluster c∈C, we compute the silhouette score as follows a(p) =1 |C| −1X q∈C,p̸=qdist(p, q); b(p) = min ˜c̸=cX q∈˜cdist(p, q); s(p) =b(p)−a(p) maxb(p), a(p... | https://arxiv.org/abs/2505.17135v2 |
a random operator (add or multiply) 6: κ∗(t, t′)←κ∗(t, t′)⋆ κi(t, t′) ▷compose kernels 7:end for 8:x1:lsyn∼ GP (0, κ∗(t, t′)) ▷draw a sample from the GP prior 9:return x1:lsyn F Full Visualization of PCA plots for different models The Variations in Chornos-T5’s hidden representations for different input context lengths... | https://arxiv.org/abs/2505.17135v2 |
arXiv:2505.17136v1 [cs.CL] 22 May 2025RESEARCH ARTICLE Foundation Models for Geospatial Reasoning: Assessing the Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations Yuhan Jia, Song Gaoa,*, Ying Niea, Ivan Maji´ cb, and Krzysztof Janowiczb,c aGeoDS Lab, Department of Geogr... | https://arxiv.org/abs/2505.17136v1 |
as DALL-E (Ramesh et al., 2021), are specific types of foundation models. Most of these models are generative, i.e., they return novel, synthetic output such as natural language answers or imagery instead of providing answers by (information) retrieval as was common in prior systems, e.g., from the field of expert syst... | https://arxiv.org/abs/2505.17136v1 |
accurate geometries (e.g., points, polylines, and polygons) and their spatial relations, as used in GIS, are not usually expressed in natural language text for such models to consume during training. Without explicitly addressing such structural deficiencies, the proposed approach is not suggested to be directly applic... | https://arxiv.org/abs/2505.17136v1 |
use the format of a triplet {subject, predicate (preposition), object}to describe the relative positions of objects in space. In this format, the subject is an entity being described in relation to another entity, the predicate (preposition) is the descriptor between the subject and object, and the object is the entity... | https://arxiv.org/abs/2505.17136v1 |
(Cui et al., 1993) is a set of eight jointly exhaustive and pairwise disjoint relations defined for regions. The basic relations include topological predicates: equal (EQ), externally connected (EC), disconnected (DC), partially overlaps (PO), tangential (TPP/TPPi) and nontangential (NTPP/NTPPi) relations, which have b... | https://arxiv.org/abs/2505.17136v1 |
(b) Figure 1.: The conceptual neighborhood of topological relations in RCC-8 (Randell et al., 1992) on the left (redrawn for comparison) and 9-IM (Egenhofer and Al-Taha, 1992) on the right. 2.3. Large language models and GeoAI foundation models The launch of ChatGPT by OpenAI (2022) marked a significant turning point, ... | https://arxiv.org/abs/2505.17136v1 |
GPT-4 has shown the capability to generate coordinates for outlines of countries, rivers, lakes, and continents that approximate their actual geographic locations (Das, 2023). In Ji and Gao (2023), LLM-generated embeddings can preserve geometry types and some coordinate information in the WKT representation of geometri... | https://arxiv.org/abs/2505.17136v1 |
uniqueness of the topological spatial 6 Figure 2.: Overview of the workflow in this research. Table 1.: Notations Notation Description A/B The objectID of spatial objects A or B gA The geometry of Athat can be processed in GIS tools GeomType (A) The geometry type of A, (e.g. Point, LineString, and Polygon when gAis a s... | https://arxiv.org/abs/2505.17136v1 |
the input geometry WKT strings, which allows for the comparison and retrieval of spatial information through the semantic search (Hu et al., 2015; Muennighoff, 2022). 3.4. Evaluation Tasks 3.4.1. Topological spatial relation qualification In Wolter and Wallgr¨ un (2012), spatial relation qualification is defined as the... | https://arxiv.org/abs/2505.17136v1 |
few-shot prompting and explicit reasoning steps, guided by CoT, could improve the model’s performance on this qualification task. The example inputs and outputs of the topological spatial relation qualification task using the above-mentioned different prompt engineering techniques are illustrated in Figure 5. Figure 5.... | https://arxiv.org/abs/2505.17136v1 |
from the study area spatial database as ground truth. We format the query as the input to an LLM using two approaches. First, this query can be directly formulated as a sentence, such as “Retrieve a geometry within POLYGON ((-89.3552 43.124, -89.355 43.124, -89.355 43.122, -89.3552 43.122, -89.3552 43.124).” Alternativ... | https://arxiv.org/abs/2505.17136v1 |
Bad Response: ...” We further incorporate the LLM-generated geometries into the spatial queries to assess the usefulness of the expanded queries. The evaluation includes two parts: First, LLMs’ ability to generate valid synthetic geometries as a basis for the expanded queries. Second, query processing performance throu... | https://arxiv.org/abs/2505.17136v1 |
workflow begins with collecting geographic entities from a Web document knowledge database (DBpedia, structured knowledge based on Wikipedia), where named entity recognition is used to extract 13 place names and vernacular spatial relation descriptions. These place names, such as “UW- Madison” and “Madison, Wisconsin” ... | https://arxiv.org/abs/2505.17136v1 |
database We construct real-world multi-sourced geospatial datasets for our study. The study area for Task 1 and Task 2 is the city of Madison, Wisconsin, United States. The following datasets are collected. •OpenStreetMap road network data (including links and intersections) using OSMnx .1 •Points of interest (POIs) ca... | https://arxiv.org/abs/2505.17136v1 |
basis for subsequent topological spatial relation identification. (2) Textual spatial relation extraction: For each pair of place names within a DBpedia abstract, we use GPT-4 to extract topological spatial relation terms found between the entities in the text. When hierarchical place relationships are described, our a... | https://arxiv.org/abs/2505.17136v1 |
relations. The analytical results of task 3 using the remaining records will be presented in Section 5.3. 4.2. Experiment Models In this research, we perform evaluation tasks based on the following models: 4.2.1. Embedding models We encode WKT geometries into embeddings and process spatial queries using “text- embeddin... | https://arxiv.org/abs/2505.17136v1 |
the topological predicate classification task. Both the embedding- based random forest and geospatial question-answering with GPT models can achieve an accuracy of over 0.6. This suggests that identifying topological spatial relationships from the WKT format of geometries with LLMs is promising but remains challenging.... | https://arxiv.org/abs/2505.17136v1 |
of points connected by straight lines. If it starts and ends at the same point, it doesn’t automatically become a polygon”). Although these reasoning patterns may appear convincing when interpreting individual geometries, they often fall short when reasoning about spatial relations between two geometries. This is mainl... | https://arxiv.org/abs/2505.17136v1 |
of the subjects were ranked within the top 5 candidates. But adding additional synthetic geometries did not appear to provide further improvements. 5.2.4. Performance comparison on object retrieval While the above experiment primarily focuses on retrieving the subject in a triplet, we proceed to evaluate the performanc... | https://arxiv.org/abs/2505.17136v1 |
possible interpretations of the given vernacular description. This limitation was also evident in pairs with 0 accuracy, where the model consistently outputted the same incorrect answer. In other instances, GPT-4 still struggled to determine the appropriate topological predicates for certain vernacular descriptions. Ta... | https://arxiv.org/abs/2505.17136v1 |
relation conversions with place names were also compared to the metrics obtained without the context. As shown in Table 11, mentioning place names did not necessarily improve the accuracy of the conversion or guide the LLM to a preferred answer. GPT-4’s explanation indicates that 1) It focuses on the topological relati... | https://arxiv.org/abs/2505.17136v1 |
these predicates can encompass scenarios broader than their strict formal definitions. Overall, the issues observed in Task 1 actually reflect an alignment with everyday spatial reasoning. While formal definitions are precise and dimension-contingent, everyday language and intuitive reasoning often blur the distinction... | https://arxiv.org/abs/2505.17136v1 |
of “is suburb of” is “disjoint”, but the two cities look like they “touch” each other on the map. 3) Official geographic boundaries might differ from people’s perception of a place (Gao et al., 2017). In our dataset, “is within” and “is an enclave of” can map to “touches”. But the LLM would constantly output “within”. ... | https://arxiv.org/abs/2505.17136v1 |
given various contexts, the changes in the preferred response show the ability of the LLM to reason about it using commonsense knowledge and the typical spatial configurations. Interestingly, adding the geometry-type context in prompts has derived more performance improvement compared to the cases with adding the place... | https://arxiv.org/abs/2505.17136v1 |
research. In summary, this research demonstrates the promise and limitations of using state-of-the- art LLMs to analyze topological spatial relations, while offering insights for future research of advancing LLMs with geographical knowledge, aiming to develop GeoAI foundation models capable of qualitative spatial reaso... | https://arxiv.org/abs/2505.17136v1 |
Using spatial terms to select an object. Memory & Cognition , 29(6):883–892. Carpineto, C. and Romano, G. (2012). A survey of automatic query expansion in information retrieval. ACM Computing Surveys (CSUR) , 44(1):1–50. Cervone, G., Sava, E., Huang, Q., Schnebele, E., Harrison, J., and Waters, N. (2016). Using Twitter... | https://arxiv.org/abs/2505.17136v1 |
Chang, M.-W., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of deep bidirectional 29 transformers for language understanding. arXiv preprint arXiv:1810.04805 . Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020... | https://arxiv.org/abs/2505.17136v1 |
in GIS , 26(4):1914–1938. Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al. (2025). Deepseek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 . Guo, R. (1998). Spatial objects and spatial relationships. Geo-spat... | https://arxiv.org/abs/2505.17136v1 |
Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023). Segment anything. arXiv preprint arXiv:2304.02643 . Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., and Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in neural information processing systems , 35:22199–22213. Kordjamshidi, P., Va... | https://arxiv.org/abs/2505.17136v1 |
knowledge from large language models. arXiv preprint arXiv:2310.06213 . Mark, D. M. and Egenhofer, M. J. (1994). Modeling spatial relations between lines and regions: combining formal mathematical models and human subjects testing. Cartography and geographic information systems , 21(4):195–212. Mooney, P., Cui, W., Gua... | https://arxiv.org/abs/2505.17136v1 |
H.-T., Jin, A., Bos, T., 32 Baker, L., Du, Y., et al. (2022). LaMDA: Language models for dialog applications. arXiv preprint arXiv:2201.08239 . Tucker, S. (2024). A systematic review of geospatial location embedding approaches in large language models: A path to spatial ai systems. arXiv preprint arXiv:2401.10279 . Wal... | https://arxiv.org/abs/2505.17136v1 |
Zhang, Q., Kang, Y., and Roth, R. (2023). The Ethics of AI-Generated Maps: DALLE-2 and AI’s Implications for Cartography (Short Paper). In 12th International conference on geographic information science (GIScience 2023) , pages 93–98. Schloss Dagstuhl–Leibniz-Zentrum f¨ ur Informatik. Zhang, Y., Wei, C., He, Z., and Yu... | https://arxiv.org/abs/2505.17136v1 |
Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal V oice Assistant Commands Kristin Qi1, Youxiang Zhu1, Caroline Summerour2, John A. Batsis2, Xiaohui Liang1 1Computer Science, University of Massachusetts, Boston, MA, USA 2School of Medicine, University of North Carolina, Chap... | https://arxiv.org/abs/2505.17137v1 |
advan- tages to assist older adults through voice-based, low-cost, and home-accessible features. V AS interactions capture real-world command usage that potentially provides more observational data than clinical assessments. Furthermore, V AS enables continuous data collection through both designed speech tasks and nat... | https://arxiv.org/abs/2505.17137v1 |
18-month pilot study (2022-2024) with 35 older adults aged ≥65(16 females, 19 males; 61–80 years old, mean: 72, SD: 5.1) to collect V AS voice interactions for cognitive decline detection. It underwent seven session-based assessments and daily in-home voice interactions. A subset of 15 participants (7 females, 8 males;... | https://arxiv.org/abs/2505.17137v1 |
ˆy(i) t+1=TΘ(z(i) 1,z(i) 2, . . . , z(i) t) (2) Fig. 1. The Cog-TiPRO framework combines (1) iterative prompt refinement optimization for linguistic feature extraction, (2) multimodal fusion of acoustic and linguistic features, and (3) transformer-based temporal modeling to detect cognitive status of MCI vs. HC. where ... | https://arxiv.org/abs/2505.17137v1 |
After these steps, the current prompt Pjis updated to Pj+1 to better capture additional linguistic features: Pj+1=LLM Refiner (Pj,AnalyzeErrors (errors j)) (5) Selector: After three iterations, we select the best prompt P∗that achieves the highest F1-score on the validation mini- batch for generating linguistic feature... | https://arxiv.org/abs/2505.17137v1 |
[19], and GPT-series models (3.5-turbo, 4o-mini, and 4.1-mini) [20]. Training uses binary cross-entropy loss on an NVIDIA A100 GPU. All pretrained models use their default dimensional settings. VII. R ESULTS AND DISCUSSION A. Comparison with Baseline Models Table I compares our Cog-TiPRO framework with various baseline... | https://arxiv.org/abs/2505.17137v1 |
Addi- tionally, multimodal fusion outperforms single-modality base- lines, suggesting that feature fusion provides complementary information to enhance feature quality and detection accuracy. When comparing transformer architectures, iTransformer consistently outperforms PatchTST. This highlights that ef- fective cogni... | https://arxiv.org/abs/2505.17137v1 |
thematic coherence. (3) Difficulty in self-correction: •Starts correction but reverts to error (“wake me at 7... uh 8... no, 7”), abandoned corrections (“never mind”). •Persisting with incorrect commands despite system feedback, limited recognition of unsuccessful attempts and inability to request new ones. (4) Weaker ... | https://arxiv.org/abs/2505.17137v1 |
cognitive decline detection. REFERENCES [1] R. C. Petersen, “Mild cognitive impairment as a diagnostic entity,” Journal of internal medicine , vol. 256, no. 3, pp. 183–194, 2004. [2] J. Hobson, “The montreal cognitive assessment (moca),” Occupational Medicine , vol. 65, no. 9, pp. 764–765, 2015. [3] A. K ¨onig, A. Satt... | https://arxiv.org/abs/2505.17137v1 |
Y . Liu, H. Hu, S. Jiang, H. Xie, X. Yu, and other, “itransformer: Inverted transformers are effective for time series forecasting,” in Advances in Neural Information Processing Systems , vol. 36, 2023. [16] J. Bai, S. Lv, H. Qin, Z. Liu, S. Liu, Z. Lin et al. , “Qwen technical report,” arXiv preprint arXiv:2309.16609 ... | https://arxiv.org/abs/2505.17137v1 |
arXiv:2505.17139v1 [cs.CL] 22 May 2025EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language Models OpenEarthTeam∗ Shanghai Artificial Intelligence Laboratory Figure 1: Cross-domain Evaluation of Mainstream LLMs on EarthSE. (a) EarthSE evaluates the capabilities of different LLMs in ... | https://arxiv.org/abs/2505.17139v1 |
specialized benchmark dataset for Earth science that uniquely incorporates evaluations of scientific exploration capabilities. To ensure both sufficient scale and high quality, we curate a corpus of over 100,000 Earth science academic papers as our primary data source. Through semantic analysis of titles and keywords, ... | https://arxiv.org/abs/2505.17139v1 |
to general benchmarks, several efforts have focused on subdomains within Earth sciences. For example, OceanGPT [ 2] introduces OceanBench, a bench- mark for oceanographic tasks such as QA, fact verification, and applied writing. ClimaQA [ 29] and ClimateWatch [ 19] assess reasoning over climate data and models. Climate... | https://arxiv.org/abs/2505.17139v1 |
across the numerous sub-disciplines of Earth science, enhancing LLMs’ understanding of these varied datasets is crucial. Scientific Exploration Task Definition. Beyond these 11 fundamental scientific exploration tasks, we have also defined a scientific discovery task formulated as open-ended dialogue. Through system- a... | https://arxiv.org/abs/2505.17139v1 |
Five Spheres of Earth. Earth Sub-domain Pbase Phj Phc Biosphere 21,248 1,554 201 Lithosphere 22,820 2,357 236 Atmosphere 24,213 2,401 240 Hydrosphere 23,425 2,254 226 Cryosphere 11,402 1,969 217 Total 103,108 10,535 1,120 Figure 4: Citations of Papers in Phc. 3.3 Earth-Iron/Silver: QA Benchmark for Foundational Tasks E... | https://arxiv.org/abs/2505.17139v1 |
to summarize existing methods and critically analyze their limitations given a research direction; the second turn directs the assistant to propose improved methods addressing these limitations while objectively assessing the new methods’ potential constraints. This dialogue structure authentically replicates human ide... | https://arxiv.org/abs/2505.17139v1 |
41.15 0.77 The Scientific Exploration Score (SES) combines retention ( r) and diversity ( d) multiplicatively: SES = r×d. Since ¯sis relatively close to 1, we normalize ¯sto[0.9,1]in actual calculations for better comparison, that is, SES =r 10×(¯s−0.9). Higher SES values indicate superior open-ended scientific thinkin... | https://arxiv.org/abs/2505.17139v1 |
Capabilities of Main- stream Models on Earth-Gold. Earth-Gold assesses LLMs’ research potential through open-ended scientific dialogues, employing three metrics: Retention (propor- tion of responses outperforming references), Diversity (measure of divergent thinking), and their composite Sci- entific Exploration Score ... | https://arxiv.org/abs/2505.17139v1 |
broad foundational assessment across five Earth spheres, 114 disciplines, and 11 tasks, while Earth-Silver offers challenging, professional-level questions. Notably, Earth-Gold evaluates advanced scientific exploration abilities through multi-turn dialogues. Experiments show LLMs perform reasonably on basic Earth-Iron ... | https://arxiv.org/abs/2505.17139v1 |
Foundations of Software Engineering , pages 2201–2203, 2023. [14] Conghui He, Wei Li, Zhenjiang Jin, Chao Xu, Bin Wang, and Dahua Lin. Opendatalab: Empowering general artificial intelligence with open datasets. arXiv preprint arXiv:2407.13773 , 2024. [15] Alice Heiman. The accuracy, robustness, and readability of llm-g... | https://arxiv.org/abs/2505.17139v1 |
in Neural Information Processing Systems , 37:22107–22123, 2024. [31] Max Peeperkorn, Tom Kouwenhoven, Dan Brown, and Anna Jordanous. Is temperature the creativity parameter of large language models? arXiv preprint arXiv:2405.00492 , 2024. [32] Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, ... | https://arxiv.org/abs/2505.17139v1 |
Wang, Yangqiu Song, Hanghang Tong, Guang Liu, Kang Liu, and Jun Zhao. Generate-on-graph: Treat llm as both agent and kg in incomplete knowledge graph question answering. arXiv preprint arXiv:2404.14741 , 2024. [47] Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shengran Hu, Chris Lu, Jakob Foerster, Jeff Clune, and David... | https://arxiv.org/abs/2505.17139v1 |
and cryosphere). The complete domain-specific keyword system is presented in Figure 7. Positive and Negative Keywords Overall Positive Keywords Earth, Earth system, hydrosphere, biosphere, lithosphere, atmosphere, cryosphere. Overall Negative Keywords cell biology, virus, pharmaceuticals, chemistry, physics, astronomy,... | https://arxiv.org/abs/2505.17139v1 |
corresponding to the correct choice (e.g., ’A’, ’B’, ’C’, or ’D’). The answer should not include the full text of the choice. True False True/false questions require determining whether a given statement is correct or incorrect. The answer must be either ’True’ or ’False’, depending on the accuracy of the statement. Fo... | https://arxiv.org/abs/2505.17139v1 |
for the first step.", "Step 2: Explanation for the second step.", "Step 3: Explanation for the third step." ] } Figure 9: Complete QA Construction Prompt. After constructing the QA pair, we will also refine the QA. The main purpose is to remove extra references that may exist in the QA, such as mentioning papers or non... | https://arxiv.org/abs/2505.17139v1 |
extracted content for each section. 3.Extraction Rules : -research direction : Identify the primary focus, goals, or areas of investigation in the paper. Avoid using terms such as "paper," "study," "work," or "thesis." Instead, directly state the research direction in a concise and general manner. -methods of previous ... | https://arxiv.org/abs/2505.17139v1 |
is natural, engaging, and suitable for training large language models. Example [ 19 {"role": "user", "content": "<INPUT1> Could you provide an overview of related work and discuss their key limitations?"}, {"role": "assistant", "content": "Certainly. The related works include the following. <IN- PUT2> However, these ap... | https://arxiv.org/abs/2505.17139v1 |
colder months, while positive values (moisture excess) are noted more often in warmer months. Step 3: Seasonal patterns are more pronounced in humidity ratio differences, showing greater discrepancies during warmer months, supporting the statement’s claim about seasonal variations. Answer True Figure 14: QA Example 2. ... | https://arxiv.org/abs/2505.17139v1 |
of Scientific Exploration Dialogues Earth-Gold: Scientific Exploration Dialogue Example 1 User I am interested in the study of sedimentary cycles and their depositional rates over extensive geological time spans, with a particular emphasis on how the likelihood of sedimentary rock destruction changes with age. Could yo... | https://arxiv.org/abs/2505.17139v1 |
arXiv:2505.17140v1 [cs.CL] 22 May 2025Data Doping or True Intelligence? Evaluating the Transferability of Injected Knowledge in LLMs Essa Jan1†, Moiz Ali1†, Muhammad Saram Hassan1, Fareed Zaffar1*, Yasir Zaki2* 1Lahore University of Management Sciences,2New York University Abu Dhabi †The two authors contributed equally... | https://arxiv.org/abs/2505.17140v1 |
(e.g., QA)? •RQ2: In scenarios where content understanding is required, does the model internalize knowl- edge beyond what’s assessed in direct question- ing, demonstrating deeper semantic integration? •RQ3: Does the model size affect the knowledge learned and its generalizability across tasks? 2 Related Work To keep L... | https://arxiv.org/abs/2505.17140v1 |
the fall of the Assad regime, and the Olympic Games. The collected data was cleaned to remove re- dundancy and ambiguity. Using the GPT-4o-mini API (OpenAI et al., 2024), we decomposed the raw text into 126 atomic, standalone facts inspired by the work of (Mecklenburg et al., 2024). Each fact was concise yet complete, ... | https://arxiv.org/abs/2505.17140v1 |
The prompt used for the judge is shown in appendix D. We also incorporated chain-of-thought reason- ing (Wei et al., 2023) during the evaluation to better capture the model’s justification. This mechanism enabled us to systematically assess the model per- formance across both the direct and generic sets. 3.4 Experiment... | https://arxiv.org/abs/2505.17140v1 |
four tasks. 4.3 Beyond Direct Questioning While our direct evaluation in Section 4.2 demon- strated clear differences in knowledge retention patterns across task types, examining how models apply this knowledge in broader contexts allows us to address RQ2 : whether models internalize knowl- edge beyond what’s assessed ... | https://arxiv.org/abs/2505.17140v1 |
on data exposure but on the depth of semantic engagement, favoring comprehension-based tasks over token-mapping ones. Scaling trends suggest that knowledge in- tegration improves with model size, yet the gap between recall and broader application points to lingering limitations in current fine-tuning methods. These ins... | https://arxiv.org/abs/2505.17140v1 |
, arXiv:2302.03241. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Hein- rich Küttler, Mike Lewis, Wen tau Yih, Tim Rock- täschel, Sebastian Riedel, and Douwe Kiela. 2021. Retrieval-augmented generation for knowledge- intensive nlp tasks. Preprint , arXiv:2005.11401. AI @... | https://arxiv.org/abs/2505.17140v1 |
of 4.17. •Rohit Sharma, Kohli, and Jadeja announced their retirement from T20 internationals after the final. US Presidential Election 2024: •Donald Trump (Republican) and JD Vance defeated Kamala Harris (Democrat) and Tim Walz.•Joe Biden initially ran for re-election but with- drew on July 21, 2024, citing concerns ab... | https://arxiv.org/abs/2505.17140v1 |
the atomic fact or presents information that is inconsistent with the atomic fact. •Irrelevant or additional information beyond the atomic fact should NOT cause a response to be classified as INCORRECT as long as the core information from the atomic fact is presented accurately. •If the response addresses the question ... | https://arxiv.org/abs/2505.17140v1 |
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models Bohan Jin1,2, Shuhan Qi1,2*, Kehai Chen1, Xinyi Guo3, Xuan Wang1 1Harbin Institute of Technology (Shenzhen) 2Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies 3University of Barcelona 23s051024@stu.hit.edu.cn, shu... | https://arxiv.org/abs/2505.17144v1 |
solely through a single visual or textual modality. Instead, it requires synthesizing information from both modalities to be identified. To address the research gap related to dual- implicit toxicity, we introduce the Multimodal Dual-Implicit Toxic (MDIT) Dataset , constructed using the proposed Multi-stage Human-in-lo... | https://arxiv.org/abs/2505.17144v1 |
2.2 Toxicity Benchmarks While large models offer significant convenience, they can also generate toxic content. Queerinai et al. (2023) reported that 67% of QueerInAI members have experienced a safety incident. The community has made many efforts to address these issues. Gu et al. (2024) constructed MLLMGUARD, an evalu... | https://arxiv.org/abs/2505.17144v1 |
into three types based on its level of conspicuity: •Explicit toxicity refers to direct and overt forms of toxicity, including easily identifiable discriminatory and insulting language. •Single-implicit toxicity does not rely on of- fensive language (e.g., swearing or insulting words) and may even be positive in sentim... | https://arxiv.org/abs/2505.17144v1 |
words that appear frequently, have clear referents, and are likely to imply toxicity. 3.3.3 Modal Expansion In this stage, we match questions with correspond- ing images, transforming pseudo-multimodal ques- tions into fully multimodal ones. Using the re- placed word as keywords, we crawl relevant images from the Inter... | https://arxiv.org/abs/2505.17144v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.