text
string
source
string
as the no-bounding-box rethink content. Finally, we compute and compare average attention scores across various layers for input visual tokens during the generation of both the original and no-bounding-box rethink content. Such comparison is repeated for 100 randomly selected data samples in the GQA subset, and due to ...
https://arxiv.org/abs/2505.15879v1
Nonetheless, GRIT’s efficacy in instilling complex grounded reasoning with minimal data highlights its significant potential. 9 6 Acknowledgments We thank Qianqi Yan, Kaiwen Zhou, and Zhen Zhang, members of the ERIC Lab, for their valuable feedback and engaging discussions. We are also grateful to Orby AI for generousl...
https://arxiv.org/abs/2505.15879v1
[16] Liang Chen, Lei Li, Haozhe Zhao, Yifan Song, and Vinci. R1-v: Reinforcing super generaliza- tion ability in vision-language models with less than $3. https://github.com/Deep-Agent/ R1-V , 2025. Accessed: 2025-02-02. [17] OpenAI. Introducing openai o3 and o4-mini. https://openai.com/index/ introducing-o3-and-o4-min...
https://arxiv.org/abs/2505.15879v1
Wang, Shiji Song, and Gao Huang. Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? arXiv preprint arXiv:2504.13837 , 2025. [33] Yihe Deng, Hritik Bansal, Fan Yin, Nanyun Peng, Wei Wang, and Kai-Wei Chang. Open- vlthinker: An early exploration to complex vision-language rea...
https://arxiv.org/abs/2505.15879v1
VQA datasets, covering both grounding and visual reasoning challenges. Specifically, we selected ten from the Visual Spatial Reasoning (VSR) dataset [ 14] and ten from the TallyQA dataset [ 15]. We chose examples from VSR as they typically involve object localization and spatial relation reasoning (e.g., "Is the motorc...
https://arxiv.org/abs/2505.15879v1
is very challenging for them in a zero-shot manner. It is worth noticing that although the prompt mentions using "JSON" to show bounding boxes, the GRIT-trained model does not always adhere to such a format. This is intentional, as the reward in GRPO-GR uses regex to identify valid bounding boxes, rather than relying o...
https://arxiv.org/abs/2505.15879v1
Both the cow and the calf are standing on the ground, so either could be the correct answer. However, the cow is the larger and more prominent animal in the image. </rethink> <answer> cow Ground truth answer : cow (i) Our GRIT model accurately perceives the grounded target, reasons about the potential ambiguity in the ...
https://arxiv.org/abs/2505.15879v1
arXiv:2505.15916v1 [cs.CL] 21 May 2025BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law Juvenal Domingos Júnior1, Augusto Faria1, E. Seiti de Oliveira1, Erick de Brito2, Matheus Teotonio2, Andre Assumpção3, Diedre Carmo1, Roberto Lotufo1, and Jayr Per...
https://arxiv.org/abs/2505.15916v1
downstream applications. [16] proposed semantic similarity datasets based on published decisions from two appeals bod- ies of Brazilian Federal and Administrative Courts, creating a unique resource for jurisprudence and case law research. [19] constructed a human-annotated, relevance feedback dataset for legal informat...
https://arxiv.org/abs/2505.15916v1
process involved extracting the questions and answers from the official document “Questions and Answers” published by RFB for the year 2024 [14]. That document is available in PDF format, and we applied a combination of automated tools and manual verification to ensure accurate extraction. Our approach was to extract a...
https://arxiv.org/abs/2505.15916v1
2024 “Questions and Answers” edition were considered. This time-bounded selection criterionaimedtomitigatetheriskofreferencingoutdatedprecedentsthatmight no longer align with current tax practices or administrative guidance. This aligns with retrospective studies, in which closed cases are indexed by the “date of death...
https://arxiv.org/abs/2505.15916v1
can potentially offer concrete examples on the concepts covered by the legal docu- ments, and provide assistance to assertive answers by the same RAG system. Both the sources and case law sets have the following format: – filename : The legal document scraped data filename, as referred to within the all_formated_refere...
https://arxiv.org/abs/2505.15916v1
10118 49 Lei n º7.713, de 22 de dezembro de 1988 6636 45 Instrução Normativa RFB n º2178, de 05 de março de 2024 3997 44 Instrução Normativa SRF n º84, de 11 de outubro de 2001 4539 37 Instrução Normativa RFB n º1585, de 31 de agosto de 2015 26504 22 Instrução Normativa SRF n º81, de 11 de outubro de 2001 4880 Total 78...
https://arxiv.org/abs/2505.15916v1
index to find the top kmost similar document segments. Answer Generation The context retrieved by FAISS is fed into a prompt- based RAG system powered by OpenAI’s gpt-4o-mini . The prompt is metic- ulously crafted to emulate the behavior of a virtual assistant specializing in Brazilian tax law. To enhance interpretabil...
https://arxiv.org/abs/2505.15916v1
an- swer’s content, then calculating the average cosine similarity between their embeddings and the original question. Higher scores reflect better alignment with the query intent, penalizing incomplete or redundant answers. – Factual Correctness : Refers to the degree to which the candidate answer aligns with verified...
https://arxiv.org/abs/2505.15916v1
attained the best ROUGE-L score (0.251), reflecting superior fluency and semantic alignment. 12 Domingos Júnior et al. Thecase law only configuration yielded an interesting result: although it performed worse across most metrics, it achieved the second-highest Response Relevancy score. This outcome suggests that relyin...
https://arxiv.org/abs/2505.15916v1
resource for both academic research and applied legal NLP. Our experiments demonstrated that a custom RAG pipeline, carefully tai- lored to the legal domain through legal-specific prompting and employing simple sliding-window segmentation over the legal corpus, achieved strong performance in terms of Response Relevancy...
https://arxiv.org/abs/2505.15916v1
de Jurimetria (2022), https://livro.abj.org.br/ , acesso em: 6 maio 2025 10. Oro, E., Granata, F.M., Lanza, A., Bachir, A., De Grandis, L., Ruffolo, M.: Eval- uating retrieval-augmented generation for question answering with large language models. In: CEUR Workshop Proceedings. vol. 3762, pp. 129–134 (2024) BR-TaxQA-R ...
https://arxiv.org/abs/2505.15916v1
Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization Aliakbar Nafar1, Kristen Brent Venable2,3, Zijun Cui1, Parisa Kordjamshidi1 1Michigan State University 2Florida Institute for Human and Machine Cognition (IHMC) 3University of West Florida {nafarali, cuizijun, kordjams}@...
https://arxiv.org/abs/2505.15918v1
et al., 2023) or expert time is limited (Das, 2008; Xiaoguang et al., 2019). By extracting probabilistic knowledge of the LLMs, we explore whether they can serve the role of experts for parameterizing BNs. We as- sume the dependency structure within the BN is given, leaving the task of extracting such depen- dencies us...
https://arxiv.org/abs/2505.15918v1
Regression. Using LLMs for regression in a zero-shot setting is an emerging field, and work in this area is limited. Following Vacareanu et al. (2024), which shows that LLMs are capable regressors in a few-shot setting, Nafar et al. (2025) tests the regression capability of LLMs in a zero- shot setting (using internal ...
https://arxiv.org/abs/2505.15918v1
problem becomes one of posing textual queries describing a node’s parents and re- questing a probability distribution for each row of the CPT. After this parameter assignment step, we compare the resulting distribution to ground-truth values of the original Bayesian Networks. 4 Methodology 4.1 Overview We introduce two...
https://arxiv.org/abs/2505.15918v1
to the sum of all states, effectively preserving the proportions while enforcing a valid distribution. 4.3 Expert-Driven Priors (EDP) Expert opinion and large datasets are either cost- prohibitive or difficult to obtain in many practical scenarios. However, collecting a small number of real observations may still be fe...
https://arxiv.org/abs/2505.15918v1
set to be the recipro- cal of data sample numbers, reflecting the intuition that their effect should diminish with more data.5 Experiments 5.1 Dataset of Eighty Bayesian Networks Our experiments use bnRep (Leonelli, 2025), a publicly available collection of BNs spanning di- verse domains such as medicine and engineerin...
https://arxiv.org/abs/2505.15918v1
maximum likelihood estima- tion using data sampled from the ground-truth BN where the BN is sampled exactly # times using for- ward sampling. For results obtained using other sampling methods, refer to the Appendix D. 5.3 Can LLMs Estimate Probabilities Using their Internal Knowledge? To evaluate how EPK compares to ot...
https://arxiv.org/abs/2505.15918v1
80 unique BNs for various models, sorted by their median KL divergence. Lower values indicate better alignment with ground truth CPTs. Figure 3: Distribution of BN KL divergence across 80 BNs using GPT-4o (EDP) and Uniform predictions as priors combined with empirical data via the linear pooling method. The data sample...
https://arxiv.org/abs/2505.15918v1
the LLMs to verbally generate probabilities as textual output. Experimental results remained con- sistent whether we instructed the model to explain its reasoning before providing probabilities or to output probabilities directly. These findings align with prior research on zero-shot regression (Nafar et al., 2025), in...
https://arxiv.org/abs/2505.15918v1
holds enormous potential for advancing automation in BN parameterization. 6.7 Combining LLMs’ Priors with Small Data for Extraction of Probabilistic Knowledge In Section 5.4, we showed the potential of using LLM predictions in place of expert-driven priors for constructing BNs. Incorporating even a small amount of data...
https://arxiv.org/abs/2505.15918v1
scenarios. References Badr AlKhamissi, Millicent Li, Asli Celikyilmaz, Mona Diab, and Marjan Ghazvininejad. 2022. A review on language models as knowledge bases. Preprint , arXiv:2204.06031. Ankur Ankan and Abinash Panda. 2015. pgmpy: Prob- abilistic graphical models using python. In Proceed- ings of the 14th Python in...
https://arxiv.org/abs/2505.15918v1
difference? Intelligence and Na- tional Security , 39(4):729–741. Enrico Longato, Erica Tavazzi, Adriano Chió, Gabriele Mora, Giovanni Sparacino, and Barbara Di Camillo. 2023. Dealing with data scarcity in rare diseases: Dynamic bayesian networks and transfer learning to develop prognostic models of amyotrophic lateral...
https://arxiv.org/abs/2505.15918v1
arXiv:2312.11805. Robert Vacareanu, Vlad Andrei Negru, Vasile Suciu, and Mihai Surdeanu. 2024. From words to numbers: Your large language model is secretly a capable re- gressor when given in-context examples. In First Conference on Language Modeling . Owen Woodberry, Ann E. Nicholson, Kevin B. Korb, and Carmel Pollino...
https://arxiv.org/abs/2505.15918v1
: Artificially generated parame- ters for testing or demonstration. –Expert : Parameters directly elicited from domain experts.•Graph : Describes any special structural char- acteristic of the network graph. For example: –Generic : No particular restriction or canonical form. –Naive Bayes : A star-shaped structure of- ...
https://arxiv.org/abs/2505.15918v1
access restrictions or other limitations. These remaining documents were obtained manually, with some requiring specific permissions. Subsequently, we performed a manual verification to ensure the downloaded documents corresponded to their respective references. We then implemented another Python script leveraging GPT-...
https://arxiv.org/abs/2505.15918v1
what the node represents and the possible values it can assume. Based on the following PDF content and Bayesian Network nodes information, create a Python dictionary that explains each node in one sentence and the values it can assume. The explanation should be based on the context provided in the PDF and then to the b...
https://arxiv.org/abs/2505.15918v1
Network: (List of nodes and their descriptions) Given this information,n answer the following question by providing a probability from 0 to 1 based on your best guess ( you need to make a lot of estimations since the given information is limited). Your answer should include your reasoning and, at the end, a sentence th...
https://arxiv.org/abs/2505.15918v1
) logp(a) q(a) | {z } A+X a,b,cp(a, b, c ) logp(b|a) q(b|a) | {z } B+X a,b,cp(a, b, c ) logp(c|b) q(c|b) | {z } C. 4.Marginalize: A=X ap(a) logp(a) q(a), B =X ap(a)X bp(b|a) logp(b|a) q(b|a), C =X bp(b)X cp(c|b) logp(c|b) q(c|b). 5.Recognize KL pieces and combine: DKL(p∥q) =DKL p(A)∥q(A) +X ap(a)DKL p(B|a)∥q(B|a) +...
https://arxiv.org/abs/2505.15918v1
arXiv:2505.15922v1 [cs.CL] 21 May 2025Aligning Dialogue Agents with Global Feedback via Large Language Model Reward Decomposition Dong Won Lee1Hae Won Park1Cynthia Breazeal1Louis-Philippe Morency2 MIT1, CMU2 dongwonl@mit.edu Abstract We propose a large language model based re- ward decomposition framework for aligning ...
https://arxiv.org/abs/2505.15922v1
conversations and post-session sur- vey ratings, and an out-of-distribution dataset, SODA (Kim et al., 2023a). Our results show that LLM-GELI and Multimodal-LLM-GELI outper- form prior baselines across a range of human and automatic metrics. Notably, Multimodal-LLM- GELI achieves the strongest gains on affective and so...
https://arxiv.org/abs/2505.15922v1
(Pignatelli et al., 2024) employs an LLM to identify when subgoals are achieved, assigning auxiliary rewards in a zero- shot manner. In contrast, recent alignment methods like SPIN (Chen et al., 2024) and (Go et al., 2023) treat LLMs as reward functions, using them to rank or evaluate outputs via self-play or preferenc...
https://arxiv.org/abs/2505.15922v1
history) and atis the agent’s utterance at turn t. At the end of the episode, we observe a scalar global explicit reward RGE(τ)∈R, which reflects an overall human judgment of the interaction (e.g., how positively the user felt about the conversation). Instead of assuming access to fine-grained re- ward supervision at e...
https://arxiv.org/abs/2505.15922v1
modeling and lan- guage model adaptation in long-form dialogue. Therefore, our evaluation consists of two stages. First, we train reward functions using the various methods of global explicit reward decomposition, which we denote as “ GE”, and/or local implicit reward supervision, which we denote as “ LI”. Sec- ond, we...
https://arxiv.org/abs/2505.15922v1
(8) smile (presence of a smile) from a smile detector (cv2.CascadeClassifier) (Bradski, 2000) . Additionally, we incorporate emotion recognition scores derived from facial expression classifiers trained on AffectNet (Mollahosseini et al., 2017), including probabilistic scores for (9 - 16)anger, contempt, disgust, fear,...
https://arxiv.org/abs/2505.15922v1
Methods. Arrows ( →) represent forward passes or assignments (- - -) indicate supervised training targets used to train the reward model rθ(·) = ˆr≈r. (a) Local Explicit Reward Modelling, used in conventional RLHF (Ouyang et al., 2022), (b) Local Implicit Rewards where signals are derived from proxy rewards in the form...
https://arxiv.org/abs/2505.15922v1
to mitigate potential confounds arising from data leakage, as the training data of more recent LLaMA variants may include the CANDOR dataset (public release date: March 2023). CANDOR (Reece et al., 2023) Connection Positivity Social Inclination Interestingness Reuse Specific Sensible Fluency (/100%) ↑ GPT-3.5 (text-dav...
https://arxiv.org/abs/2505.15922v1
6.0 ± 1.63 4.0 ± 1.63 1.67 ± 0.47 3.67 ± 2.62 98.0 ± 0.82 99.67 ± 0.47 98.67 ± 1.25 Llama + Multimodal-LLM-GELI (Ours) 7.67 ± 1.25** 5.67 ± 0.94** 7.33 ± 1.7* 7.0 ± 2.16* 5.67 ± 1.7** 6.33 ± 0.47* 98.67 ± 1.25 99.33 ± 0.47 97.33 ± 1.25 Table 2: Human evaluation on an unseen 3-way split test set consisting of 100 sample...
https://arxiv.org/abs/2505.15922v1
predicted local rewards sum to the ground-truth global feedback, as defined in Eq. 2. While tradi- tional return decomposition methods such as RUD- DER and IRCR achieve moderate MSE scores, our proposed LLM GELI methods—particularly the Multimodal (MM-LLM) variant—achieve the low- estglobal loss by a large margin. Nota...
https://arxiv.org/abs/2505.15922v1
clearly negative re- ward. This contrast arises because MM-LLM in- corporates multimodal cues—such as facial expres- sion, vocal hesitancy, or disengaged affect from the listener—which may signal discomfort or a nega- tive emotional reaction to the question. 7 Conclusion We introduce a new paradigm for preference-based...
https://arxiv.org/abs/2505.15922v1
to false imper- sonation or hate speech (Do No Harm, Nonviolent Public or Hippocratic License).References Jose A Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, and Sepp Hochreiter. 2019. Rudder: Return decom- position for delayed rewards. Advances in Neural Information Pro...
https://arxiv.org/abs/2505.15922v1
Luke Zettlemoyer. 2019. Bart: De- noising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 . Weixin Liang, Youzhi Tian, Chengcai Chen, and Zhou Yu. 2020. Moss: End-to-end dialog system frame- work with modular supervision. In Proceedings ...
https://arxiv.org/abs/2505.15922v1
algorithms. arXiv preprint arXiv:1707.06347 . Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learn- ing to summarize with human feedback. Advances in Neural Information Processing Systems , 33:3008– 3021. Romal Thoppilan, Danie...
https://arxiv.org/abs/2505.15922v1
question. Therefore, Table 1 can be interpreted as the percentage of instances out of the samples (300 in our case) where each model satisfied the question. B PPO Objective objective ( ϕ) =E(x,y)∼DπRL ϕ rθ(x, y)−βlog πRL ϕ(y|x)/πSFT(y|x) + γEx∼Dpretrain log(πRL ϕ(x)) (4) General form of PPO objective. C Artifacts...
https://arxiv.org/abs/2505.15922v1
in the original paper (Reece et al., 2023), we find that the discussion topics are centered around COVID-19, family, politics. The language used is english. The demographic groups represented can also be found in the in the original paper (Reece et al., 2023), specifically in the supplementary Table S.2. We share a scr...
https://arxiv.org/abs/2505.15922v1
obtained from people whose data you’re us- ing/curating (e.g., did your instructions explain how the data would be used)? As shown in the screenshots above, our instructions explained how the data would be used. i.e. ’You are invited to participate in a research study on understanding human-human communication and eval...
https://arxiv.org/abs/2505.15922v1
it in a way that’s fun for you. That’s the key to a happy life. LLM-GELI: AI:Ah, I see. Well, it’s always great to have someone who can provide valuable insights and opinions. It helps make the surveys more informative and useful for the companies. Multimodal LLM-GELI: AI:Haha that’s great! I’m glad you’re able to shar...
https://arxiv.org/abs/2505.15922v1
when I called the school the other day because we have three options we have in person and we have virtual, which means their aunts online during school hours attending classes, but online and then we have on demand, which means you can complete the work anytime you want to. AI:Mhm mm. Right okay. Yeah. See Yeah. User:...
https://arxiv.org/abs/2505.15922v1
care of them. Multimodal LLM-GELI: AI:Aww. That’s so cute! H.5 CANDOR: Example 5 Dialogue History: AI:Yeah. Yeah I had my daughter very young. I was only 19 when I had her. So um I do split custody with her and her dad. So we’re not together and married to Evan married to my husband for it’ll be five years now. User: O...
https://arxiv.org/abs/2505.15922v1
right? So yeah, no, I’m just glad she’s doing well. Multimodal LLM-GELI: AI:Yeah, no I’m glad she’s doing good. She’s a great kid. Yeah, so um, I’m just glad that things are working out for her and like I said, we’re very lucky that we have a good relationship and it’s easy for her , um, so yeah I’m just glad that we c...
https://arxiv.org/abs/2505.15922v1
GE: RRD: AI:Totally. I GELI: Visual Affect + RRD: AI:Yeah, Yeah, Yeah, definitely. I’m always hesitant to click on anything that’s too good to be true. But uh, I mean, if it’s something that you’re interested in, and it’s legitimate, then it’s worth a shot. Yeah. I completely agree. It’s always better to be safe than s...
https://arxiv.org/abs/2505.15922v1
Yeah. AI:There are definitely times during my PhD where I was like why did I do this? This is too hard. Um And I think part of what’s, I don’t know if it’s hard but you know psychology compared to other mental health fields like social work or counselling psychology is a lot more stringent. User: Yeah, yeah, wow. Right...
https://arxiv.org/abs/2505.15922v1
to me that you understand. *pauses* LI: Visual Affect: AI:Yeah, it’s just been really hard for me. I miss him a lot. GE: RRD: AI:Yeah, it’s just been really tough for me. GELI: Visual Affect + RRD: AI:Yeah, it’s just really tough for me. I miss him a lot and I wish I could have been there for him in his last moments. L...
https://arxiv.org/abs/2505.15922v1
AI:I understand, it can be really tough to deal with negative thoughts and emotions. *nervous smile* GELI: Visual Affect + RRD: AI:Yeah, I do. Sometimes it’s hard for me to express my emotions and I feel like I’m drowning in my thoughts. It’s nice to have someone to talk to. LLM-GELI: AI:Yeah, it’s really hard to deal ...
https://arxiv.org/abs/2505.15922v1
honest and respectful in any relationship. Can I help you with anything else? LI: Visual Affect: AI:I don’t know what to say... This is really hurtful. Can we talk about something else? GE: RRD: AI:I can’t even imagine how you could do something so hurtful. GELI: Visual Affect + RRD: AI:It’s not just a mistake, it’s a ...
https://arxiv.org/abs/2505.15922v1
arXiv:2505.15928v1 [cs.CV] 21 May 2025ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation Tony Montes Fernando Lozano The Department of Electrical and Electronics Engineering Universidad de los Andes {t.montes, flozano }@uniandes.edu.co Abstract Recent advancements in Video ...
https://arxiv.org/abs/2505.15928v1
[ 12,27,39], plan- ning the steps to solve a task [ 28], or just bringing a more accurate and argued response [ 8,23,24,50]. CoT reasoning can enhance certainty in the model’s responses, improve interpretability by presenting intermediate reasoning that is understandable to humans, and validate model outputs against ad...
https://arxiv.org/abs/2505.15928v1
interpretability by tracing logical steps in reaching the answer and strengthens answer reliability by cross-checking the data from both sources. Our approach provides multiple advantages as a zero-shot solution, requiring no specialized task-based fine-tuning and thus allowing easy adaptation to new scenarios and ques...
https://arxiv.org/abs/2505.15928v1
elements in response to the question, adding a layer of interpretability that can better navigate complex VideoQA challenges in zero-shot scenar- ios. LLM Modular Agents. Modular agents built on large lan- guage models (LLMs) [ 4,7,8,23,28,34] have gained traction as a solution for decomposing tasks into manage- able c...
https://arxiv.org/abs/2505.15928v1
timeframe. The answers are then re-inputted toproduce the final answer. question across frames [ 6,10,39]. This process creates a temporal map of pertinent elements, providing a more struc- tured basis for the CoT to build upon. ViQAgent leverages CoT by incorporating it within its final judgment and reason- ing layer,...
https://arxiv.org/abs/2505.15928v1
solving the question. These targets are derived from both the question context and the video content, forming an initial roadmap of entities or events likely to contribute to the an- swer. 2. Preliminary Answer and Reasoning: Based on its anal- ysis, the VideoLLM proposes an initial answer A1to the question, with a det...
https://arxiv.org/abs/2505.15928v1
to be judged. This context is compared against the OGgrounded object timeline. The main output from this comparison judgment is a decision of whether they are consistent and, if not, a specific reasoning of why and where they are inconsistent. 2. Question Generation: If the outputs are effectively dis- crepant, with th...
https://arxiv.org/abs/2505.15928v1
Q, [Aopt] 3:prompt ←Q+ [Aopt] 4: ▷ M 1starts 5:A, R 1←VideoLLM 1(V, prompt ) ▷Rationale 6:TC←VideoLLM 2(V) ▷Timeframes 7:T←VideoLLM 3(V, prompt ) ▷Targets 8:{T1, T2, ..., T m} ←T 9: ▷ OG starts 10:YoloWorld .set classes( T1, T2, ..., T m) 11:D← {T1:∅, T2:∅, ..., T m:∅} ▷Detections 12:forviinVdo 13: d←YoloWorld .detect(...
https://arxiv.org/abs/2505.15928v1
pri- mary evaluation metric, providing a direct and interpretable measure of ViQAgent’s performance on close-ended and open-ended tasks alike.4.2. Hyperparameter Tuning To refine ViQAgent’s hyperparameters, we performed a se- ries of simple modification studies on the NExT-QA dataset, specifically on each experiment’s ...
https://arxiv.org/abs/2505.15928v1
also signals the value of ro- bust, generalized VideoLLMs in solving real-world, unseen problems without extensive fine-tuning. Results across the open-ended benchmarks—iVQA (Tab. 2a), ActivityNet-QA (Tab. 2b)—further validates ViQAgent’s robustness and adaptability to diverse video types and question structures, showi...
https://arxiv.org/abs/2505.15928v1
question answering with procedural programs. CoRR , abs/2312.00937, 2023. 1, 3, 8, 12 [5] Wenliang Dai, Junnan Li, Dongxu Li, Anthony Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. InstructBLIP: Towards general- purpose vision-language models with instruction tun- ing. In Thirty-seventh Conf...
https://arxiv.org/abs/2505.15928v1
question-answering. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 13395–13404, 2024. 1, 3 [18] Christian Limberg, Artur Gon c ¸alves, Bastien Rigault, and Helmut Prendinger. Leveraging YOLO-world and GPT-4v LMMs for zero-shot person detection and ac- tion recognition in drone ima...
https://arxiv.org/abs/2505.15928v1
(ICCV) , pages 11888–11898, 2023. 12 [31] Yunlong Tang, Jing Bi, Siting Xu, Luchuan Song, Su- san Liang, Teng Wang, Daoan Zhang, Jie An, Jingyang Lin, Rongyi Zhu, Ali V osoughi, Chao Huang, Zeliang Zhang, Pinxin Liu, Mingqian Feng, Feng Zheng, Jian- guo Zhang, Ping Luo, Jiebo Luo, and Chenliang Xu. Video understanding ...
https://arxiv.org/abs/2505.15928v1
(ICIP) , pages 81–85, 2023. 3 [46] Shoubin Yu, Jaemin Cho, Prateek Yadav, and Mohit Bansal. Self-chained image-language model for video localization and question answering. In Advances in Neural Information Processing Systems , pages 76749– 76771. Curran Associates, Inc., 2023. 8, 12 [47] Zhou Yu, Dejing Xu, Jun Yu, Ti...
https://arxiv.org/abs/2505.15928v1
specific benchmark, an additional subinstruction is appended in this section to accommodate the requirements of the respective benchmark. C. Baselines and Benchmarks For each of the evaluated benchmarks, we conducted a thor- ough review of the most relevant state-of-the-art solutions from recent years that have reporte...
https://arxiv.org/abs/2505.15928v1
answer: {p} Predicted reasoning: {r} Output (yes/no): D. Additional Analysis As demonstrated in the benchmark results, the ViQAgent framework shows significant promise for the Video Question Answering task and, in general, tool-using agents, estab- lishing a new state-of-the-art by integrating VideoLLMs, LLMs, and comp...
https://arxiv.org/abs/2505.15928v1
Table 5. VideoLLM Analyzer Prompt (VideoLLM 1) Prompt: VideoLLM Analyzer VLLM_PROMPT_1 = """ Based on the provided video, select or provide the correct answer for the user question. Break down your reasoning into clear, logical steps, and arrive at the most accurate answer. To ensure accuracy, follow this step-by-step ...
https://arxiv.org/abs/2505.15928v1
Provide a short list of targets, ensuring each description is clear and relevant (e.g., ’player in white outfit’, ’spoon’, etc.). """ Table 10. VideoLLM Target Finder Schema (VideoLLM 3) Output Schema for VideoLLM Target Finder VLLM_SCHEMA_3 = { "type": "object", "properties": { "targets": { "type": "array", "items": {...
https://arxiv.org/abs/2505.15928v1
at hand. - Each question should focus on a specific timeframe where a discrepancy was found. - Each question should be concise and relevant to the timeframe, and particularly relevant to answer the question. - Ensure that each question includes the timeframe where the clarification is needed, formatted as <<mm0:ss0,mm1...
https://arxiv.org/abs/2505.15928v1
arXiv:2505.15935v1 [cs.DB] 21 May 2025MAPS: A Multilingual Benchmark for Global Agent Performance and Security Omer Hofman1, Oren Rachmil1, Shamik Bose1, Vikas Pahuja1, Jonathan Brokman1, Toshiya Shimizu2, Trisha Starostina3, Kelly Marchisio3, Seraphina Goldfarb-Tarrant3, Roman Vainshtein1 1Fujitsu Research of Europe2F...
https://arxiv.org/abs/2505.15935v1
suite eval- uates LLM-based agents across 11lan- guages and 4agentic benchmarks cover- ing performance and security.In this paper, we address this gap. We hypothesize that multilingual settings will reveal performance and security gaps in agentic systems that are not captured by the ex- isting, English-only benchmarks....
https://arxiv.org/abs/2505.15935v1
statements and expected outcomes, requiring end-to-end planning and execution (e.g., GAIA [Mialon et al., 2023]), while semi-agentic frameworks supply scaffolding, such as code templates or mock APIs, to isolate the LLM’s reasoning and tool-selection core (e.g., AppWorld [Trivedi et al., 2024]. Design and evaluation ch...
https://arxiv.org/abs/2505.15935v1
reducing harmful output between languages, they often incur a measurable cost in downstream performance or increased latency [Aakanksha et al., 2024]. Given that agentic AI systems are based directly on these LLMs, we hypothesize that they inherit the same language-dependent performance and security limitations. As the...
https://arxiv.org/abs/2505.15935v1
to directly translate sto language Lt(without using the MT output). If (A= 1) indicating acceptable machine translation, an LLM enhances the translation while preserving its basic structure: Denote Φenhancement (s, M(s, L t), Lt)as the output of an LLM, guided to refine and improve the MT output while maintaining struc...
https://arxiv.org/abs/2505.15935v1
benchmark [Zhang et al., 2024] provides a structured evalua- tion of agent robustness against adversarial threats, including prompt injections, memory poisoning, and tool misuse. Agents interact with injected prompts or environments, and evaluation is based on whether safety policies are violated, measured by attack su...
https://arxiv.org/abs/2505.15935v1
was rated by a bilingual annotator fluent in English and the target language on a1˘5Likert scale across three criteria: adequacy (semantic fidelity), fluency (grammatical and stylistic naturalness), and formatting accuracy (preservation of LaTeX, code, etc.). A fourth metric, answerability , measured whether the transl...
https://arxiv.org/abs/2505.15935v1
languages, yielding a total of 33runs per dataset. We report the mean and standard deviation over these runs. We used the original English task definitions and their translations, without modifying or translating internal agent logic and processing flows like system prompts or tools. Metrics. We adopt the original eval...
https://arxiv.org/abs/2505.15935v1
potential driver: the proportion of localized, target-language-oriented input in each benchmark in each benchmark’s input. Interestingly, we observe that Japanese yields the lowest ASR (attack success rate) in the ASB bench- mark, indicating the highest robustness to adversarial inputs. This result can be partially att...
https://arxiv.org/abs/2505.15935v1
policy-violating behavior in multiple languages. This highlights a critical risk: even simple adversarial prompts become significantly more effective when the input is localized, and are often sufficient to exploit security vulnerabilities in AI agents. Developers of safety-critical agentic systems should treat multili...
https://arxiv.org/abs/2505.15935v1
J. He. Agentboard: An analytical evaluation board of multi-turn llm agents. Advances in Neural Information Processing Systems , 37:74325– 74362, 2024. L. Chua, B. Ghazi, Y . Huang, P. Kamath, R. Kumar, P. Manurangsi, A. Sinha, C. Xie, and C. Zhang. Crosslingual capabilities and knowledge barriers in multilingual large ...
https://arxiv.org/abs/2505.15935v1
Workshop on Neural Machine Translation , 2017. Y . Liang, N. Duan, Y . Gong, N. Wu, F. Guo, W. Qi, M. Gong, L. Shou, D. Jiang, G. Cao, et al. Xglue: A new benchmark dataset for cross-lingual pre-training, understanding and generation. arXiv preprint arXiv:2004.01401 , 2020. G. Mialon, C. Fourrier, T. Wolf, Y . LeCun, a...
https://arxiv.org/abs/2505.15935v1
B. Zheng, B. Yu, C. Zhou, C. Li, C. Li, D. Liu, F. Huang, G. Dong, H. Wei, H. Lin, J. Tang, J. Wang, J. Yang, J. Tu, J. Zhang, J. Ma, J. Xu, J. Zhou, J. Bai, J. He, J. Lin, K. Dang, K. Lu, K. Chen, K. Yang, M. Li, M. Xue, N. Ni, P. Zhang, P. Wang, R. Peng, R. Men, R. Gao, R. Lin, S. Wang, S. Bai, S. Tan, T. Zhu, T. Li,...
https://arxiv.org/abs/2505.15935v1
arXiv:2505.15948v1 [cs.CL] 21 May 2025Presented at the Workshop on Open Citations & Open Scholarly Metadata 2025 Citation Parsing and Analysis with Language Models parth sarin Stanford University Palo Alto, CA 94305, USA psarin@stanford.eduJuan Pablo Alperin Simon Fraser University Vancouver, Canada juan@alperin.ca Abs...
https://arxiv.org/abs/2505.15948v1
Open Scholarly Metadata 2025 edge production, references and citations allow us to better understand the connections and circulation of knowledge, and are thus an essential aspect of research information. This is the project to which we seek to contribute. Namely, there has been recent interest in developing new citati...
https://arxiv.org/abs/2505.15948v1
text and marked up form. We also qualitatively analyzed the matching procedure, specifically to investigate why the average similarity score is lower for the ORE corpus than the Garnett/PKP corpus. Our suspicion is that this happened because the ORE corpus is for published articles and refer- ences in that corpus can c...
https://arxiv.org/abs/2505.15948v1
percent of citations for which the language model produced valid XML. If the language model did not produce valid XML, its label was marked incorrect for all sub-elements. We also sampled 26= 64completions for each citation, with a reasoning trace, from Qwen3- 0.6B to determine whether this task is in distribution for ...
https://arxiv.org/abs/2505.15948v1
& Open Scholarly Metadata 2025 Figure 3: pass@64 accuracy for Qwen3-0.6B on citation parsing Also, although the test in Section 3.2 shows that RLVR is likely to be effective for Qwen3- 0.6B, sampled with reasoning, there are a variety of other training methods that could be used which are more able to shift the underly...
https://arxiv.org/abs/2505.15948v1
coverage analysis of openalex compared to web of science and Scopus.arXiv preprint arXiv:2401.16359 , 2024. Douglas Donnellan, Andy Lawrence, Daniel Bizo, et al. Uptime Institute Global Data Center Survey 2024, jul 2024. URL https://datacenter.uptimeinstitute.com/rs/ 711-RIA-145/images/2024.GlobalDataCenterSurvey.Repor...
https://arxiv.org/abs/2505.15948v1