text string | source string |
|---|---|
as shown in Figure 9. System Prompt: Aconversation between User and Assistant .The user asks aquestion, and theAssistant solves itstep bystep.The assistant first thinks about thereasoning process inthe mind andthen provides theuser with theanswer, i.e.,reasoning process here ...theanswer is: \boxed{answer }. Figure 9: ... | https://arxiv.org/abs/2505.15692v2 |
new mean becomes 84. Since there are now 10 scores, the sum of these 10 scores is.3.The highest score is 98. Therefore, the sum of the remaining 11 scores (excluding the highest and lowest scores) is Solving for the lowest score, we get: 4.Check what the question asks. The question asks for the lowest score, and we fou... | https://arxiv.org/abs/2505.15692v2 |
Can Large Language Models be Effective Online Opinion Miners? Ryang Heo Yongsik Seo Junseong Lee Dongha Lee† Yonsei University {ryang1119, ysseo, brulee, donalee}@yonsei.ac.kr Abstract The surge of user-generated online content presents a wealth of insights into customer pref- erences and market trends. However, the hi... | https://arxiv.org/abs/2505.15695v1 |
a deeper understanding of user preferences. Despite these advances, existing approaches still face two critical limitations. (1) Underrepresen- tation of real-world input complexity : Previ- ous benchmarks predominantly focus on single- sentence reviews (Peng et al., 2019; Cai et al., 2021; 1arXiv:2505.15695v1 [cs.CL] ... | https://arxiv.org/abs/2505.15695v1 |
of ( entity, feature, opinion ) tuples reflect- ing explicit user perspectives, and (2) context-rich, opinion-centric summaries organized around key thematic insights from a marketer’s viewpoint. Building upon this benchmark, we introduce two complementary tasks: (1) Feature-centric opin- ion extraction (FOE) evaluates... | https://arxiv.org/abs/2505.15695v1 |
different sources: Blog ,Re- view Site ,Reddit , and YouTube . Blog and re- view site provide detailed long-form posts and spe- cific car reviews, while reddit and youtube capture multi-threaded and single-threaded discussions, re- spectively. Specifically, we curate the sources of each website from Feedspot,2a platfor... | https://arxiv.org/abs/2505.15695v1 |
as input. Then, the same five human annotators review each sum- mary from the perspective of a marketing manager and select the highest-quality one that best captures the opinions in the final tuples at the topic level. Similar to the tuple annotation process, we design detailed annotation guidelines to ensure consiste... | https://arxiv.org/abs/2505.15695v1 |
tuples even when surface forms differ significantly, used the prompt shown in Table 17. Note that for both RM and CM, we measure recall by counting each gold tuple at most once to avoid double counting, even if multiple predicted tuples match the same gold tu- ple. For all evaluation metrics, we primarily use the F1 sc... | https://arxiv.org/abs/2505.15695v1 |
EM 0.4505 0.4722 0.4215 L-RM 0.4584 0.4754 0.4244 S-RM 0.5514 0.5531 0.4937 CM 0.8337 0.8155 0.7279 Table 3: Correlation coefficients between each metric and human judgment ( p-value < 0.05) based on pair- wise comparisons by five human evaluators. Detailed experimental settings are provided in Appendix B.2. such as Ll... | https://arxiv.org/abs/2505.15695v1 |
ples does not keep pace. Notably, recall improves significantly across most models but eventually reaches a plateau, where the rate of increase di- minishes. This implies that LLMs recognize a fixed set of opinions within the content, makingContent : Interior materials remain perfectly adequate for the price of the tru... | https://arxiv.org/abs/2505.15695v1 |
structures. Additionally, they achieve relatively high BS; their performance on A3CU remains substantially lower, suggesting that LLMs often capture surface-level semantic similarity but struggle to reflect deeper, human- aligned content understanding. Thus, to thoroughly gauge LLMs’ abstractive strengths—particularly ... | https://arxiv.org/abs/2505.15695v1 |
F1 510 15 20 25 30 35 40 45 1 2 3 4 5 6 1 3 5 7 9 10 200 400 600 800 1000 Number of Tokens202530354045A3CU 510 15 20 25 30 35 40 45 Number of Tuples 1 2 3 4 5 6 Number of Entities 1 3 5 7 9 10 Number of Users 31.6%35.3% 14.4% 8.0%10.7% 0102030405060 15.0%22.4% 21.6% 15.8% 8.9%7.0%5.1%2.4% 1.8%53.8% 21.4% 8.8%5.8%3.0%7.... | https://arxiv.org/abs/2505.15695v1 |
benchmark, which encompasses a wide spectrum of realistic online content and enables comprehensive investigation of both extraction and abstractive capacities of LLMs. 6 Conclusion In this paper, we introduce OOMB, a novel bench- mark designed to assess LLMs’ capabilities in both structured opinion extraction and insig... | https://arxiv.org/abs/2505.15695v1 |
we aim to foster academic progress in generative event extraction research. References Anthropic. 2024. Claude 3.5 haiku and sonnet. Yinhao Bai, Zhixin Han, Yuhua Zhao, Hang Gao, Zhuowei Zhang, Xunzhi Wang, and Mengting Hu. 2024. Is compound aspect-based sentiment analysis addressed by LLMs? In Findings of the Associat... | https://arxiv.org/abs/2505.15695v1 |
Danielle Pintz, Danny Livshits, Danny Wyatt, David Esiobu, Dhruv Choudhary, Dhruv Mahajan, Diego Garcia-Olano, Diego Perino, Dieuwke Hupkes, Egor Lakomkin, Ehab AlBadawy, Elina Lobanova, Emily Dinan, Eric Michael Smith, Filip Radenovic, Francisco Guzmán, Frank Zhang, Gabriel Synnaeve, Gabrielle Lee, Georgia Lewis An- d... | https://arxiv.org/abs/2505.15695v1 |
Paranjape, Bing Liu, Bo Wu, Boyu Ni, Braden Han- cock, Bram Wasti, Brandon Spence, Brani Stojkovic, Brian Gamido, Britt Montalvo, Carl Parker, Carly Burton, Catalina Mejia, Ce Liu, Changhan Wang, Changkyu Kim, Chao Zhou, Chester Hu, Ching- Hsiang Chu, Chris Cai, Chris Tindal, Christoph Fe- ichtenhofer, Cynthia Gao, Dam... | https://arxiv.org/abs/2505.15695v1 |
Kumar, Vishal Mangla, Vlad Ionescu, Vlad Poenaru, Vlad Tiberiu Mihailescu, Vladimir Ivanov, Wei Li, Wenchen Wang, Wen- wen Jiang, Wes Bouaziz, Will Constable, Xiaocheng Tang, Xiaojian Wu, Xiaolan Wang, Xilun Wu, Xinbo Gao, Yaniv Kleinman, Yanjun Chen, Ye Hu, Ye Jia, Ye Qi, Yenda Li, Yilin Zhang, Ying Zhang, Yossi Adi, ... | https://arxiv.org/abs/2505.15695v1 |
Chenguang Zhu. 2023a. G-eval: Nlg evaluation using gpt-4 with better human align- ment. Preprint , arXiv:2303.16634. Yixin Liu, Alexander Fabbri, Yilun Zhao, Pengfei Liu, Shafiq Joty, Chien-Sheng Wu, Caiming Xiong, and Dragomir Radev. 2023b. Towards interpretable and efficient automatic reference-based summarization ev... | https://arxiv.org/abs/2505.15695v1 |
Power, Boris Power, Elizabeth Proehl, Raul Puri, Alec Radford, Jack Rae, Aditya Ramesh, Cameron Raymond, Francis Real, Kendra Rimbach, Carl Ross, Bob Rotsted, Henri Roussez, Nick Ry- der, Mario Saltarelli, Ted Sanders, Shibani Santurkar, Girish Sastry, Heather Schmidt, David Schnurr, John Schulman, Daniel Selsam, Kyla ... | https://arxiv.org/abs/2505.15695v1 |
in Natural Language Pro- cessing , pages 12061–12081, Miami, Florida, USA. Association for Computational Linguistics. Tejpalsingh Siledar, Swaroop Nath, Sankara Muddu, Rupasai Rangaraju, Swaprava Nath, Pushpak Bhat- tacharyya, Suman Banerjee, Amey Patil, Sudhan- shu Singh, Muthusamy Chelliah, and Nikesh Gar- era. 2024.... | https://arxiv.org/abs/2505.15695v1 |
A. Choquette-Choo, Danila Sinopalnikov, David Wein- berger, Dimple Vijaykumar, Dominika Rogozi ´nska, Dustin Herbison, Elisa Bandy, Emma Wang, Eric Noland, Erica Moreira, Evan Senter, Evgenii Elty- shev, Francesco Visin, Gabriel Rasskin, Gary Wei, Glenn Cameron, Gus Martins, Hadi Hashemi, Hanna Klimczak-Pluci ´nska, Ha... | https://arxiv.org/abs/2505.15695v1 |
qin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuancheng Ren, Xuejing Liu, Yang Fan, Yang Yao, Yichan... | https://arxiv.org/abs/2505.15695v1 |
with detailed feedback, making them rich in straightforward user opinions. YouTube We gathered comments from automo- tive YouTube channels10 11listed by Feedspot12, focusing on channels with large subscriber bases providing car reviews and analysis. When YouTu- bers share their vehicle reviews, viewer opinions and reac... | https://arxiv.org/abs/2505.15695v1 |
sentiment expressions, highlighting their specialized nature. Points be- tween clusters reflect nuanced or polysemous opin- ions, suggesting the need for flexible sentiment understanding models. B Experimental Details B.1 Evaluation Models Proprietary LLMs We used the most up-to-date versions of OpenAI APIs16and Anthro... | https://arxiv.org/abs/2505.15695v1 |
without dis- tortion and check for any hallucinations. •Coverage : Evaluate whether the summary effec- tively captures and represents the key opinions expressed in the review. •Specificity : Evaluate whether the summary presents meaningful and relevant details rather than being vague or overly generic. •Insightfulness ... | https://arxiv.org/abs/2505.15695v1 |
ble 17. •LLM-Judge Evaluation : The prompt for evaluating the LLM-Judge is presented in Ta- ble 18, 19, 20, 21, 22 and 23. 18 Attribute RangeContent TypeTotal Ratio(%) Blog Reddit Review Site YouTube Tuples≤10 8 79 14 125 226 37.7 ≤15 14 49 33 32 128 21.3 ≤20 19 21 33 21 94 15.7 ≤25 20 15 13 7 55 9.2 ≤30 20 8 8 8 44 7.... | https://arxiv.org/abs/2505.15695v1 |
6.32 7.97 29.30 16.52 20.93 21.08 11.37 14.78 14.08 7.59 9.87 Open-source LLMs Llama3-8B-Instruct 8.49 6.28 7.17 21.33 15.43 17.80 15.52 10.84 12.77 10.59 7.39 8.71 Llama3-70B-Instruct 7.26 5.57 6.27 19.94 15.18 17.15 13.80 10.37 11.85 9.44 7.09 8.10 Gemma2-9B-it 6.37 4.51 5.25 17.73 12.59 14.64 11.73 8.55 9.89 7.73 5.... | https://arxiv.org/abs/2505.15695v1 |
Llama3-8B-Instruct 9.82 7.56 8.54 21.31 16.41 18.54 28.46 21.92 24.77 64.15 50.72 54.89 Llama3-70B-Instruct 5.90 4.63 5.19 17.16 13.48 15.10 24.33 19.11 21.41 66.23 52.56 57.13 Gemma2-9B-it 7.24 5.22 6.06 16.99 12.25 14.24 21.87 15.77 18.32 63.11 48.66 53.49 Gemma2-27B-it 6.39 5.63 5.99 16.98 14.95 15.90 23.97 21.10 22... | https://arxiv.org/abs/2505.15695v1 |
10.54 30.70 86.36 29.41 Gemma2-27B-it 35.48 12.43 30.84 90.46 38.58 35.12 10.88 30.87 90.10 32.90 Qwen2.5-7B-Instruct 33.10 10.71 29.61 89.73 25.29 35.37 11.27 22.89 89.27 24.47 DeepSeek-7B-chat 33.74 9.81 29.01 83.65 29.12 36.47 10.84 32.14 77.44 27.21 Table 14: Performance comparison of different models for the OIG t... | https://arxiv.org/abs/2505.15695v1 |
grouping related opinions into high-level categories. •Line 2: Focus on the features that a user strongly praised or criticized, incorporating the intensity or frequency of opinions where applicable. •Line 3: Provide a cohesive conclusion summarizing the overarching sentiment or key takeaway from a user’s text. 4. Writ... | https://arxiv.org/abs/2505.15695v1 |
in the original text. • Score 1: The summary completely distorts the original online content and contains many incorrect information. It cannot be trusted at all. •Score 2: The summary significantly misrepresents the original online content with several incorrect information. •Score 3: The summary partially reflects th... | https://arxiv.org/abs/2505.15695v1 |
and relevant details by including concrete information rather than being vague or overly generic. Ensure that the summary provides clear, detailed points that directly relate to the review content. •Score 1: The summary is extremely vague and generic, lacking any meaningful details. It uses broad generaliza- tions with... | https://arxiv.org/abs/2505.15695v1 |
to evaluate the summary based on its Intent. Make sure you understand the following evaluation metric very clearly. Evaluation Criteria: Intent (1-5) – Evaluate whether the summary accurately preserves the author’s original tone, intent, and nuances without altering the emotional or stylistic essence of the review. Con... | https://arxiv.org/abs/2505.15695v1 |
car opinion miner for the user. I want to perform feature-centric opinion extraction which is identifying attributes, specific features, or components mentioned in the text and associating opinions with each feature. To maximize coverage and diversity, you will generate a comprehensive set of tuples using your reasonin... | https://arxiv.org/abs/2505.15695v1 |
in the sentence. •sentence_exist : Whether the sentence exists in the document on the right. •If a feature appears in the content, it is highlighted in bold red in both the Document Info and Document Text. • If an opinion appears in the document, it is highlighted in bold blue . • The evidence sentence is highlighted i... | https://arxiv.org/abs/2505.15695v1 |
(not explicitly stated in the text), label it as "NULL". This summary should be written in natural language, structured around the core features discussed, and clearly convey the most salient and recurring opinions. Step 1. Read and Understand • Thoroughly examine both the input content and the associated tuples. • Ide... | https://arxiv.org/abs/2505.15695v1 |
Check that the summary properly distinguishes between individual opinions and collective sentiments when aggregating views from multiple users. Confirm that referenced features are associated with their correct corresponding entities. (4) Check Sentiment Consistency Check for sentiment polarity errors, particularly in ... | https://arxiv.org/abs/2505.15695v1 |
years on sale.Parts availability is a bitch. Comment #11519 (Author: Person 2, Reply to reply comment #11518): Good choice. An actual car that people dont talk about. There was also the M56 with a VK56 V8 that made 420 horsepower. Also rare. Heard one with an exhaust a while ago and it sounded pretty good. Comment #115... | https://arxiv.org/abs/2505.15695v1 |
feels a touch unique.The V olvo XC60 B5 receives mixed feedback, with users appreciating its comfort and unique design, particu- larly in the R-design trim. However, software issues are a significant con- cern, as the latest 2.2 version, which includes Apple CarPlay, is buggy and unavailable for OTA updates on B5 trims... | https://arxiv.org/abs/2505.15695v1 |
the software version that enables stability for your car/trim and then turn off automatic updates in the settings. For my XC60 B5 I am going to stick with 2.1 until forced to update or until the blogs indicate V olvo and Google are aligning better. Aside from the software gremlins this SUV is comfortable, super handsom... | https://arxiv.org/abs/2505.15695v1 |
insurance, repair, and maintenance. Person 4 bluntly states that vans are inherently boxy due to their functional purpose, implying that design changes are limited by their utility. Gold Summary The Ford e-Transit receives mixed feedback, with some users criticizing its design as uninteresting and ugly due to its use o... | https://arxiv.org/abs/2505.15695v1 |
precise detail, warranting a score of 4 rather than a 5. Insightfulness : 4 Comprehensive Coverage : The summary effectively covers the key points of the review, including the issue with the battery, the software problems, and the resolution through the 2.1 software update. It emphasizes the importance of stability and... | https://arxiv.org/abs/2505.15695v1 |
are all present in the summary. This shows no significant omissions. Absence of Hallucinated Information : The summary does not introduce any information that was not present in the original text, ensuring that it stays true to the opinions and insights provided by the commenters. This maintains the integrity of the re... | https://arxiv.org/abs/2505.15695v1 |
comment within the discussion. Person 1’s dissatisfaction with the trend is clearly articulated, as is the practical- focused tone of Persons 2, 3, and 4. This indicates that the emotional elements of approval or disapproval were preserved effectively. Nuance and Specificity : The summary encapsulates the nuances in ea... | https://arxiv.org/abs/2505.15695v1 |
arXiv:2505.15696v1 [cs.CL] 21 May 2025MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation Maike Behrendt Heinrich Heine University Düsseldorf ‘maike.behrendt@hhu.deStefan Sylvius Wagner Heinrich Heine University Düsseldorf stefan.wagner@hhu.de Stefan Harmeling Technical University Dortmund ... | https://arxiv.org/abs/2505.15696v1 |
the final layer exhibit high cosine similarity due to information mixing through self- attention. Motivated by these findings, we explore incre- mental modifications to the BERT-base architec- ture for sequence classification, aiming to enhance its performance on downstream tasks. We specif- ically focus on improving t... | https://arxiv.org/abs/2505.15696v1 |
very similar and carry similar information. Recently, Warner et al. (2024) introduce Mod- ernBERT, an updated version of BERT with an increased sequence length of 8192. ModernBERT incorporates architectural improvements such as GeGLU activations (Shazeer, 2020), Flash Atten- tion (Dao et al., 2022), and RoPE embeddings... | https://arxiv.org/abs/2505.15696v1 |
a single token is passed to the classifier. However, it has been shown that other token rep- resentations in the layers of BERT also capture sentence-level representations (Rogers et al., 2020). We investigate whether the informativeness of the [CLS] token embedding can be further enhanced during fine-tuning, to improv... | https://arxiv.org/abs/2505.15696v1 |
depth information from these task-specific layers into the [CLS] embedding just before classification. Exper- imenting with different values for k, we found that k= 3works best (see A.1.1 in the Appendix).3.3 Token-Wise Attention via Additional MHA Layer. An alternative way to enrich the information in the [CLS] token,... | https://arxiv.org/abs/2505.15696v1 |
Figure 2: Comparison of four BERT architectures for sequence classification. (Left above) Classical BERT for sequence classification architecture. (Right above) Maximizing the token embeddings of the [CLS] token over the lastklayers. (Left below) Adding an additional MHA layer before classification. (Right below) MaxPo... | https://arxiv.org/abs/2505.15696v1 |
than the BERT baseline, indicating that our proposed methods for enriching the [CLS] token representation are effective. However, the magnitude of improvement varies across tasks. The Max CLS variant, which applies max- pooling over the [CLS] token representations from the last klayers, results in marginal to no improv... | https://arxiv.org/abs/2505.15696v1 |
2019; Lee et al., 2020; Dodge et al., 2020), we run all exper- iments with three different seeds for each GLUE task. We report the mean accuracy across runs (for CoLA we report Matthews correlation coefficient, for STS-B we report Spearman rank correlation),and include error bars showing the standard devia- tion of the... | https://arxiv.org/abs/2505.15696v1 |
This work does not involve the collection or use of sensitive personal data, nor does it generate or process harmful content. We use only publicly available datasets (GLUE benchmark) and follow standard evaluation protocols. Our modifications are intended to improve model efficiency and ro- bustness, particularly in lo... | https://arxiv.org/abs/2505.15696v1 |
Sabharwal, and Ashish Verma. 2020. PoWER-BERT: Acceler- ating BERT inference via progressive word-vector elimination. In Proceedings of the 37th International Conference on Machine Learning , volume 119 of Proceedings of Machine Learning Research , pages 3690–3699. PMLR. Yaru Hao, Li Dong, Furu Wei, and Ke Xu. 2020. In... | https://arxiv.org/abs/2505.15696v1 |
Linguistics , 8:842–866. Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:2002.05202 . Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. InProceed... | https://arxiv.org/abs/2505.15696v1 |
89.29 65.34 k= 3 55.35 85.95 89.78 66.06 k= 4 56.42 85.29 89.27 65.34 k= 6 55.65 85.13 89.25 65.7 k= 12 55.41 85.21 89.17 65.46 Table 6: Effect of max-pooling depth kon small GLUE tasks. k= 3generally yields best results. A Appendix A.1 Ablations We conduct ablation studies to test different mod- ifications of out arch... | https://arxiv.org/abs/2505.15696v1 |
arXiv:2505.15700v2 [cs.CL] 26 May 2025“Alexa, can you forget me?” Machine Unlearning Benchmark in Spoken Language Understanding Alkis Koudounas*1, Claudio Savelli*1, Flavio Giobergia1, Elena Baralis1 1Politecnico di Torino, Italy name.surname@polito.it Abstract Machine unlearning, the process of efficiently removing sp... | https://arxiv.org/abs/2505.15700v2 |
to han- dle the complexities of SLU tasks. To fill this gap, we introduce UnSLU-BENCH , the first comprehensive benchmark for machine unlearning in SLU. It includes four intent classification datasets in four different lan- guages: Fluent Speech Commands (FSC) [19] and SLURP [20] in English, ITALIC [21] in Italian, and... | https://arxiv.org/abs/2505.15700v2 |
gradient direction is reversed during the backpropagation to make the model forget Df. NegGrad+ ( NG+)[28,29] was proposed as an extension to Neg- ative Gradients to avoid the so-called “catastrophic forgetting” , i.e., the destruction of the model’s utility. To do this, in addition ofNGonDf,FTis done on the whole Dr. ... | https://arxiv.org/abs/2505.15700v2 |
.505 .642 26.70× UNSIR .991 1.00 .506 .447 6.550 ×.994 .998 .508 .484 6.380× BT .993 1.00 .508 .000 4.780 ×.993 .999 .504 .363 4.650 × BT-L .994 .996 .506 .431 5.870 ×.993 .997 .506 .464 5.690 × SCRUB .994 1.00 .506 .439 6.210 ×.993 .998 .508 .479 6.220 × to retrain the model from scratch. As we do not consider the cos... | https://arxiv.org/abs/2505.15700v2 |
.532 .000 1.000×.784 .736 .478 .000 1.000× FT .638 .970 .648 .000 83.78 ×.734 1.000 .611 .088 79.00 ×.638 .671 .555 .590 30.80×.711 .850 .550 .551 31.10× NG .695 .986 .604 .563 1748 × .718 .959 .587 .587 1654 × .679 .868 .603 .646 613.4 ×.590 .621 .525 .766 623.0 × NG+ .701 .995 .603 .446 41.63×.630 .852 .453 .578 39.3... | https://arxiv.org/abs/2505.15700v2 |
language (e.g., Italian, German, French). 3SpeechMASSIVE covers 12 languages, but we focus on German and French only. 4These splits are publicly available in our project repository. 107 106 105 104 103 Learning Rate0.000.250.500.751.00Macro F1 score 0.000 0.005 0.010 0.015 (MIA(u)MIA(g))2 F1T F1F MIAFigure 1: Trade-off... | https://arxiv.org/abs/2505.15700v2 |
×.436 .594 .612 .414 58.23 ×.770 1.000 .624 .338 58.86× UNSIR .565 .788 .616 .197 27.46 ×.785 1.000 .619 .114 14.23 ×.420 .591 .620 .259 14.67 ×.768 1.000 .633 .089 14.94 × BT .584 .789 .582 .489 20.02 ×.726 .945 .585 .418 10.41 ×.411 .583 .597 .409 10.60 ×.772 .981 .621 .317 10.82 × BT-L .584 .786 .576 .523 24.87 ×.72... | https://arxiv.org/abs/2505.15700v2 |
GUM scores (.563 vs .429). Unlearning in SLURP*. Table 5 finally studies the trade-off between model utility and unlearning efficacy tied to training duration. We consider SLURP*, and produce various Origi-Table 4: Unlearning metrics on SLURP*, wav2vec 2.0. Method F1T MIA Speedup NoMUS GUM Orig. .689 .628 1.000× .717 .... | https://arxiv.org/abs/2505.15700v2 |
[2] P. V oigt and A. V on dem Bussche, “The eu general data protection regulation (gdpr),” A Practical Guide, 1st Ed., Cham: Springer In- ternational Publishing , vol. 10, no. 3152676, pp. 10–5555, 2017. [3] E. Goldman, “An introduction to the california consumer pri- vacy act (ccpa),” Santa Clara Univ. Legal Studies R... | https://arxiv.org/abs/2505.15700v2 |
M. Ravanelli, P. Ignoto, V . S. Tomar, and Y . Ben- gio, “Speech model pre-training for end-to-end spoken language understanding,” in Proc. INTERSPEECH 2019 . [20] E. Bastianelli, A. Vanzo, P. Swietojanski, and V . Rieser, “SLURP: A spoken language understanding resource package,” in EMNLP , 2020. [21] A. Koudounas, M.... | https://arxiv.org/abs/2505.15700v2 |
HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases Pingqing Zheng University of Minnesota, Twin Cities Minneapolis, MN, USA pingqingzheng13@gmail.comJiayin Qin University of Minnesota, Twin Cities Minneapolis, MN, USA qin00162@umn.eduFuqi Zhang University of Minnesota, Twin Cities Mi... | https://arxiv.org/abs/2505.15701v1 |
Abstract Syntax Trees (ASTs) and Data Flow Graphs (DFGs). Using ASTs, we partition the HDL repository with about several thousand lines of code into a code graph view containing multi-level entity relationships. While DFGs provide a more precise hardware graph view of signal-level flow to reflect the circuit topology. ... | https://arxiv.org/abs/2505.15701v1 |
projects, to solve the gap in insufficient search datasets for HDL codes. •Integrating HDLxGraph with three LLMs with various scale and different coding abilities, we demonstrate the versatility of HDLxGraph on three real-world HDL tasks, i.e., code search, debugging, and completion. Experi- ments demonstrate that our ... | https://arxiv.org/abs/2505.15701v1 |
Fusion Module Decomposer Task Solver Code Semantic SearchOutputModules Blocks Signals Sim.-based ExtractResult Debugging CompletionFig. 2. The overview of our proposed HDLxGraph framework. C. HDL Code Structure Graph code views, such as AST, DFG, and Control Flow Graph (CFG), have been adopted for a more comprehensive ... | https://arxiv.org/abs/2505.15701v1 |
on Verilog, a widely used HDL language, in our implementation. Please note that, although different HDLs have different syn- tactic properties, they share the same three-level structural ab- straction, i.e., (module →block →signal) in Verilog. Specifically, we use an AST to support the code graph view that emphasizes m... | https://arxiv.org/abs/2505.15701v1 |
i…reg [3:0] data_r… always @(pos…assign out_data = d clk Module Block Signal TempFig. 3. Visualization of an example in the graph database. BLOCK ) via code encoding to facilitate semantic search. These embeddings, together with the node attributes extracted by the parser, are recorded in the database as part of the no... | https://arxiv.org/abs/2505.15701v1 |
Neo4j as the graph database, the query APIs are written in Cypher to interact with the database. 3) Cross-level Rerank. Finally, we rerank results using av- eraged similarity scores. Since the signal-level representation lacks the code context, it is challenging to directly obtain an accurate similarity score for the s... | https://arxiv.org/abs/2505.15701v1 |
code completion beyond literal text matching. C. HDL Search Benchmark Observing the absence of an HDL code search benchmark, we aim to establish a specific benchmark to address this gap. However, manually creating expert-annotated benchmark is time-consuming and labor-intensive, posing it economicallyimpractical. There... | https://arxiv.org/abs/2505.15701v1 |
HDLSearch (see Section III-C) as the benchmark with termination count 𝐾=7when generation. The generated benchmark comprises 40 module-level queries, 100 block-level queries and 200 signal-level queries, with 6,300 code blocks from 10 reposito- ries serving as distractor, i.e., retrieval scope. The evaluation focuses o... | https://arxiv.org/abs/2505.15701v1 |
Section IV-C. Evaluation Results: As shown in Figure 8, HDLxGraph consistently improves 𝑃𝑎𝑠𝑠 @1 accuracy by 3-10% across various LLMs. While our evaluation framework operates at module granularity rather than full repository scope, we strategically employ the RTLLM [48] codebase as a RAG corpus, thereby maintaining... | https://arxiv.org/abs/2505.15701v1 |
Zhao, Zhe Lin, Wenchao Ding, Xiaofeng Hou, Yu Feng, Chao Li, and Minyi Guo. Autovcoder: A systematic framework for automated verilog code generation using llms. arXiv , 2024. [10] Michael Gautschi, Pasquale Davide Schiavone, Andreas Traber, Igor Loi, Antonio Pullini, Davide Rossi, Eric Flamand, Frank Gurkaynak, and Luc... | https://arxiv.org/abs/2505.15701v1 |
via large language models. In 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD) , pages 1–9, 2023. [24] Yun-Da Tsai, Mingjie Liu, and Haoxing Ren. Rtlfixer: Automatically fixing rtl syntax errors with large language models. arXiv , 2023. [25] Zixi Zhang, Greg Chadwick, Hugo McNally, Yiren Zhao, an... | https://arxiv.org/abs/2505.15701v1 |
Leskovec. Inductive repre- sentation learning on large graphs, 2018. [40] Ahmed Allam and Mohamed Shalan. Rtl-repo: A benchmark for evaluating llms on large-scale rtl design projects. arXiv , 2024. [41] Sonnet Anthropic. Model card addendum: Claude 3.5 haiku and upgraded claude 3.5 sonnet. [42] Binyuan Hui, Jian Yang, ... | https://arxiv.org/abs/2505.15701v1 |
CODE RETRIEVAL API S API name Description Output 𝑠𝑒𝑎𝑟𝑐ℎ𝑚𝑜𝑑𝑢𝑙𝑒 Search for module Name of module 𝑠𝑒𝑎𝑟𝑐ℎ𝑏𝑙𝑜𝑐𝑘 Search for block Code of block 𝑠𝑒𝑎𝑟𝑐ℎ𝑠𝑖𝑔𝑛𝑎𝑙 Search for signal Name of signal 𝑠𝑒𝑎𝑟𝑐ℎ𝑚𝑜𝑑𝑢𝑙𝑒𝑏𝑙𝑜𝑐𝑘 Search for block in the module Code of block 𝑠𝑒𝑎𝑟𝑐ℎ𝑚𝑜𝑑𝑢𝑙𝑒𝑠... | https://arxiv.org/abs/2505.15701v1 |
arXiv:2505.15702v1 [cs.CL] 21 May 2025LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing Peng Wang1, Biyu Zhou1, Xuehai Tang1, Jizhong Han1,Songlin Hu1, 1Institute of Information Engineering, Chinese Academy of Sciences Correspondence: {wangpeng2022, zhoubiyu, tangxuehai, hanjizhong, hu... | https://arxiv.org/abs/2505.15702v1 |
capability to retain knowledge and generate fluent sentences after editing is prone to instability. Recent studies attempt to alleviate this issue by imposing supple- mentary constraints (e.g., regularized weight up- dating in RECT (Gu et al., 2024) and null space projection in AlphaEdit (Fang et al., 2025)) during par... | https://arxiv.org/abs/2505.15702v1 |
in this paper. For a input x, the hidden state hlat the l-th layer is expressed as: hl=hl−1+al+ml,al=Attnl(hl−1), ml=MLPl(al) =Wl outact(Wl in(al+hl−1)) (1) Here,alandmlare the outputs of AttnlandMLPl. MLPlcontains two linear layers with parameters Wl in∈Rd0×d1andWl out∈Rd1×d0, where d0is the intermediate dimension and... | https://arxiv.org/abs/2505.15702v1 |
the formula 4 can be derived. After obtaining ∆(t), the model parameters are updated as: W(t)=W(t−1)+∆(t). (5) By repeating this process at each timestamp t, sequential editing is achieved, enabling the model to progressively incorporate all Tbatches of new knowledge. 3 The LyapLock Framework 3.1 Constrained Sequence E... | https://arxiv.org/abs/2505.15702v1 |
the upper bound of equation 10 (for the derivation of the upper bound, see Appendix B.3), that is: min ∆(t)V·EL(t) +aZ(t)PL(t).(11) Now the original long-term optimization prob- lem 6 is decomposed into stepwise subproblems at each timestamp t. 3.3 Stepwise Editing with Long-term Guarantees After transforming Problem 6... | https://arxiv.org/abs/2505.15702v1 |
Z(t+ 1) according to Eq.7. end 4 Experiment 4.1 Setting Base LLMs. We selected three representative LLMs commonly used in the field of knowledgeediting: GPT2-XL (1.5B) (Radford et al., 2019), GPT-J (6B) (Wang and Komatsuzaki, 2021), and LLaMA3 (8B) (Meta, 2024). Baseline Methods. To compare with our method, we chose th... | https://arxiv.org/abs/2505.15702v1 |
81.68 ±0.34 69.01 ±0.30 617.04 ±0.24 30.70 ±0.12 94.34 ±0.13 90.20 ±0.20 30.74 ±0.22 Pre-edited GPT-J15.22 ±0.36 17.65 ±0.33 83.50 ±0.25 622.01 ±0.14 29.61 ±0.10 26.45 ±0.28 25.74 ±0.28 27.04 ±0.26 FT 94.56 ±0.23 77.04 ±0.36 40.71 ±0.37 327.71 ±0.86 11.11 ±0.13 61.82 ±0.35 59.24 ±0.36 13.53 ±0.19 ROME 48.71 ±0.50 49.70... | https://arxiv.org/abs/2505.15702v1 |
able to maintain a certain level of performance with more sequential edits, but when the number of sequential edits reaches 10,000 sam- ples, the performance of all baseline methods drops to almost zero. This is consistent with our previous findings that these methods cannot suppress the cumulative effect of parameter ... | https://arxiv.org/abs/2505.15702v1 |
is 41.11%. This fully demonstrates the wide applicability of our method: it can effectively be integrated with other models based on the locate-and-edit paradigm, significantly enhancing their editing performance while also bolstering their ability to maintain gen- eral capabilities. For more compatibility results on a... | https://arxiv.org/abs/2505.15702v1 |
to gener- ate and spread hate speech, false information, or harmful content, threatening social harmony and stability. Thus, it is crucial and urgent to implement effective safeguards to prevent misuse and mitigate potential harm. Therefore, we strongly advocate that researchers implement rigorous validation and oversi... | https://arxiv.org/abs/2505.15702v1 |
Process- ing, EMNLP 2023, Singapore, December 6-10, 2023 , pages 8214–8232. Association for Computational Linguistics. Tom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, and Marzyeh Ghassemi. 2023. 9 Aging with GRACE: lifelong model editing with dis- crete key-value adaptors. In Advances in Neural Informa... | https://arxiv.org/abs/2505.15702v1 |
In International Con- ference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA , volume 162 of Proceedings of Machine Learning Research , pages 15817–15831. PMLR. Michael J. Neely. 2010. Stochastic Network Optimiza- tion with Application to Communication and Queue- ing Systems . Synthesis Lectu... | https://arxiv.org/abs/2505.15702v1 |
Yuxuan Fan, Zhiyong Wu, Jingjing Xu, and Baobao Chang. 2023. Can we edit factual knowledge by in-context learning? In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023 , pages 4862– 4876. Association for Computational Linguistics. A Model ... | https://arxiv.org/abs/2505.15702v1 |
causal tracing localization, subsequent modifications will be made to the pa- rameters of the second layer of the MLP module in the model’s intermediate layer, Wl out, to achieve knowledge updating. Specifically, the model edit- ing updates the knowledge (s, r, o )in LLMs to (s, r, oc). This process can be understood a... | https://arxiv.org/abs/2505.15702v1 |
form of K0KT 0andV0KT 0in the computational formulas. Therefore, it is common practice to store only K0KT 0andV0KT 0. For more details, refer to (Meng et al., 2023). B Proof B.1 Proof of Sufficient Condition Here, we prove that the sufficient condition for the constraint to always hold is the strong stability of the vi... | https://arxiv.org/abs/2505.15702v1 |
have: a2+b2+c2+ 2a(b−c)≥2bc≥0. (39) C Experimental Setup C.1 Baseline Methods Here, we will introduce the baseline methods used in this paper, which are as follows: FT. FT is a parameter-efficient model adjustment strategy that selectively updates parameters in spe- cific layers of the model using a cross-entropy loss ... | https://arxiv.org/abs/2505.15702v1 |
neighborhood samples. Each sample includes a subject term sand a target object othat needs to be modified, as well as semantically similar and dissimilar sentences. These features enable the ef- fective assessment of a model’s generalization abil- ity and specificity. As a result, the ZsRE dataset is widely used to tes... | https://arxiv.org/abs/2505.15702v1 |
hyperparameter con- figurations for LLaMA3 are based on AlphaEdit, while those for GPT2-XL and GPT-J are adapted from MEMIT. Specifically, for LLaMA3, the edit- ing layers are set to [4,5,6,7,8]; for GPT2-XL, the editing layers are [13,14,15,16,17]; and for GPT-J, the editing layers are [3,4,5,6,7,8]. For all models, t... | https://arxiv.org/abs/2505.15702v1 |
content generated by the baseline methods often fails to include the target knowledge (Edit Target) and tends to produce a large number of meaningless characters or repeated words, which leads to poor text fluency. In contrast, 16 Table 2: Performance results of sequential editing task (2,000 Samples). Here, the abbrev... | https://arxiv.org/abs/2505.15702v1 |
We further demonstrate the performance improve- ment of our method in combination with other base- line methods across various models and datasets after editing, as shown in Figure 6, 7, 8, 9, 10. Overall, our method generally enhances both edit- ing performance and downstream task performance when combined with other ... | https://arxiv.org/abs/2505.15702v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.