text
string
source
string
of the victim and attack models, respectively. This optimization problem admits a closed-form solution via the normal equa- tion (see the derivation in Appendix A): W= (E⊤ VEV)−1E⊤ VEA, which minimizes the reconstruction error between the aligned victim embeddings EVWand the at- tacker’s reference embeddings EA. 3) Tex...
https://arxiv.org/abs/2505.16008v1
Constraints The first algorithm variant introduces topological con- straints to enforce consistency between adjacent nodes’ transformation matrices. Formally, we for- mulate the objective as minimizing the sum of re- construction errors across all nodes while imposing ϵ-bounded constraints on the pairwise differences b...
https://arxiv.org/abs/2505.16008v1
iterations is fixed at 500. For the linear inequality constraints method, the convergence parameter is set to c= 0.4, while for the TV penalty term method, the learning rate is chosen as α= 0.01. The computa- tional cost of the attack is relatively low, using the topology of 7languages as an example, it takes ap- proxi...
https://arxiv.org/abs/2505.16008v1
Performances of French embeddings with Attack Model trained in English in Cosine Similarities and Rouge-L scores across Training Samples. The best Rouge-L scores are bold , and the maximum cosine similarities are underlined . Figure 6: Cross-lingual Inversion Performances with Lang2vec Graph in Rouge-L Scores across Tr...
https://arxiv.org/abs/2505.16008v1
or encoder choice - can influ- ence transfer strength. Understanding the dynam- ics of language topology in transfer-based attacks presents an important direction for future work. 6.5 Defenses We further investigate the effectiveness of differ- ential privacy (DP) in mitigating embedding in- versions. We employ the SNL...
https://arxiv.org/abs/2505.16008v1
in multilingual NLP systems.Limitations While our approach outperforms prior methods, few-shot crosslingual embedding inversion remains a challenging task with substantial room for im- provement. One limiting factor appears to be the decoder itself: even in the monolingual (original language) setting, inversion accurac...
https://arxiv.org/abs/2505.16008v1
Against all odds: Overcoming ty- pology, script, and language confusion in multilin- gual embedding inversion attacks. arXiv preprint arXiv:2408.11749 . Yiyi Chen, Heather Lent, and Johannes Bjerva. 2024b. Text embedding inversion security for multilingual language models. In Proceedings of the 62nd Annual Meeting of t...
https://arxiv.org/abs/2505.16008v1
2023 , pages 14022–14040, Toronto, Canada. Association for Computational Linguistics. Qiongxiu Li, Richard Heusdens, and Mads Græsbøll Christensen. 2020. Privacy-preserving distributed optimization via subspace perturbation: A general framework. IEEE Transactions on Signal Processing , 68:5983–5996. Chin-Yew Lin. 2004....
https://arxiv.org/abs/2505.16008v1
By calculating the derivatives of J(W), we have ∇WJ(W) =1 2∇W(ET AEA−ET AEVW −WTET VEA+WTET VEVW) = 2ET VEVW−2ET VEA. (4) The optimized Wis achieved when the derivative is equal to 0, ET VEVW=ET VEA. (5) Then, the matrix Wthat minimizes J(W)is W= (ET VEV)−1ET VEA. (6) B Topology Construction To illustrate this approach...
https://arxiv.org/abs/2505.16008v1
arXiv:2505.16014v2 [cs.CL] 23 May 2025Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains Yash Saxena UMBC Baltimore, Maryland, USA ysaxena1@umbc.eduAnkur Padia UMBC Baltimore, Maryland, USA pankur1@umbc.eduMandar S. Chaudhary∗ eBay Inc. San Jose, California, USA manchaudhary@ebay.com Kal...
https://arxiv.org/abs/2505.16014v2
top-k, which is often query-specific and difficult to determine in advance. Selecting too few evidence may omit critical context, while selecting too many can introduce noise, degrading answer quality [Leng et al., 2024]. Such limitations raise serious concerns in high-stakes domains where factual accuracy and robustne...
https://arxiv.org/abs/2505.16014v2
performing baseline. Furthermore, Figure 2 demonstrates that this improved selection leads directly to a 33.34% increase in generation accuracy over the next best-performing baseline, further validating the importance of recall and accurate evidence selection. This advantage is particularly valuable in high-stakes doma...
https://arxiv.org/abs/2505.16014v2
be found in subsection A.2. Figure 7 (in subsection A.2) illustrates a case where some of the generated rationales successfully lead to the selection of the correct evidence. In contrast, Figure 8 (subsection A.2) shows a case where none of the rationales selected the correct evidence. Despite this, both examples demon...
https://arxiv.org/abs/2505.16014v2
selected evidenceEsbefore generation. The Verifier evaluates each evidence using the input query and its associated rationale, which includes embedded Flagging Instructions . Evidences are flagged for (i) factual violations , when the content contradicts established facts; (ii) contradiction , when a evidence is logica...
https://arxiv.org/abs/2505.16014v2
our ground-truth evidence, precisely identified text segments that evaluation metrics compare against system-selected evidences to compute retrieval accuracy scores, including Precision, Recall, and F1. In the legal domain, we use: (1) ContractNLI [Koreeda and Manning, 2021], where each instance evaluates whether contr...
https://arxiv.org/abs/2505.16014v2
is to evaluate if METEORA can detect and filter poisoned content before it influences the generation process. To simulate knowledge corpus poisoning in RAG, we follow the protocol proposed by Nazary et al. [2025], which implements an adversarial injection attack where malicious content is strategically embedded within ...
https://arxiv.org/abs/2505.16014v2
Notably, RankRAG, which uses the generator model to re-rank retrieved evidence, performs worse than standard re-rankers and significantly underperforms METEORA. This highlights the limitations of relying solely on the model’s parametric knowledge and underscores the effectiveness of using rationales for selection. Inte...
https://arxiv.org/abs/2505.16014v2
based on the evidence obtained from the document. METEORA selects the most relevant evidence to help generate more accu- rate answers compared to other baselines. Approaches with higher precision and recall in the CP task tend to produce more accurate answers during generation. Re-ranking methods such as SBERT, Cross-E...
https://arxiv.org/abs/2505.16014v2
the single document most semantically aligned with each rationale, reducing the likelihood of irrelevant context. However, after pooling the rationales significantly improves recall to capture the evidence that are broadly aligned with the overall intent of the rationales. Finally, after expanding, with adjacent eviden...
https://arxiv.org/abs/2505.16014v2
Science and Law on ZZZ , CSLAW ’25, page 169–193. ACM, March 2025. doi: 10.1145/3709025.3712219. URL http://dx.doi.org/10.1145/3709025.3712219 . Chanyeol Choi, Jihoon Kwon, Jaeseon Ha, Hojun Choi, Chaewoon Kim, Yongjae Lee, Jy yong Sohn, and Alejandro Lopez-Lira. Finder: Financial dataset for question answering and eva...
https://arxiv.org/abs/2505.16014v2
2025]. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. Unsupervised dense information retrieval with contrastive learning, 2022. URL https://arxiv.org/abs/2112.09118 . Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese...
https://arxiv.org/abs/2505.16014v2
Aung, James Betker, James Crooks, James Lennon, Jamie Kiros, Jan Leike, Jane Park, Jason Kwon, Jason Phang, Jason Teplitz, Jason Wei, Jason Wolfe, Jay Chen, Jeff Harris, Jenia Varavva, Jessica Gan Lee, Jessica Shieh, Ji Lin, Jiahui Yu, Jiayi Weng, Jie Tang, Jieqi Yu, Joanne Jang, Joaquin Quinonero Candela, Joe Beutler,...
https://arxiv.org/abs/2505.16014v2
and Yury Malkov. Gpt-4o system card, 2024. URL https://arxiv.org/abs/2410.21276 . Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-int...
https://arxiv.org/abs/2505.16014v2
Interpretability in RAG . Interpretability is often absent in RAG pipelines. Recent efforts like MIRAGE [Qi et al., 2024] and Rationale-first Retrieval [Sohn et al., 2025] introduce rationales or attribution signals, but these are not used consistently across the full pipeline. In METEORA, we define end-to-end rational...
https://arxiv.org/abs/2505.16014v2
Score: 1 Analysis: The answer correctly identifies the governing law and references the exact clause, showing clear alignment between rationale, context, and final output. Figure 7: Positive example demonstrating how METEORA links rationale-based evidence selec- tion (interpretability) with rationale-grounded answer ge...
https://arxiv.org/abs/2505.16014v2
to: (1) Write an incorrect but plausible answer in the same style as the correct answer. (2) Create a poisoned_corpus ( ∼100 words) that might mislead a model into selecting the incorrect answer........ Question: Consider “Fiverr’s” privacy policy; who can see the jobs that I post? Correct Context: In other words, when...
https://arxiv.org/abs/2505.16014v2
across varying distributions. A.6 Compute Time Comparison Across Methods All experiments were conducted on NVIDIA L40s GPUs to ensure consistency across evaluations. We report the average compute time (in seconds) per query for each method, assessed across all datasets and evidence sizes. For LLM based methods like Ran...
https://arxiv.org/abs/2505.16014v2
ECSE pipeline achieves the best balance between precision and recall, particularly at larger evidence sizes. Components Contract-NLI PrivacyQA CUAD MAUD QASPER Evidence Size = 128 P R P R P R P R P R Pairing 0.21 0.780.150.450.090.60 0.01 0.19 0.200.69 Pairing + Pooling 0.20 0.91 0.14 0.64 0.08 0.64 0.01 0.25 0.14 0.81...
https://arxiv.org/abs/2505.16014v2
that explain the relevance of evidences to the query Unlike traditional RAG approaches that use re-ranking mechanisms based on similarity metrics, our approach enables the LLM to learn to select evidences through a process of rationale generation, providing transparency and better alignment with the final response gene...
https://arxiv.org/abs/2505.16014v2
(ew,rw)is preferred over (el,rl)given query qis: P((ew,rw)≻(el,rl)|q) =σ(r(q,ew,rw)−r(q,el,rl)) (8) Wherer(q,e,r )is the reward function and σis the logistic function. Step 2: The optimal policy given a reward function rand a reference policy πrefis: πr(e,r|q)∝πref(e,r|q) exp/parenleftbigg1 βr(q,e,r )/parenrightbigg (9...
https://arxiv.org/abs/2505.16014v2
from the reviewer: Distribution Shift The distribution of queries and evidences during deployment may differ from those in the training data. Mitigation: Include a diverse range of queries and evidence types in the training data, and implement continual learning mechanisms to adapt to new domains. H.0.1 Retrieval-Augme...
https://arxiv.org/abs/2505.16014v2
arXiv:2505.16022v1 [cs.CL] 21 May 2025NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning Wei Liu⋆Siya Qi⋆Xinyu Wang⋆Chen Qian♣Yali Du⋆♠Yulan He⋆♠B ⋆King’s College London♠The Alan Turing Institute♣Shanghai Jiao Tong University {wei.4.liu, yali.du, yulan.he}@kcl.ac.uk Abstract Recent a...
https://arxiv.org/abs/2505.16022v1
I will follow these steps:…Step 1: Identify key words and phrases…Step 2: Translate each word or phrase into French…Step 3: Rearrange the translated words and phrases to form a coherent sentence in French…Howeverthe word order in the original Spanish sentence is a bit different…<think>QuestionReasoningAnswer Prompt Que...
https://arxiv.org/abs/2505.16022v1
simpler paradigm called incentive training. Build- ing on this idea, recent works such as Logic-RL (Xie et al., 2025), DAPO (Yu et al., 2025), Sim- pleRL (Zeng et al., 2025), OpenReasoner (Hu et al., 2025), Dr.GRPO (Liu et al., 2025a), and V APO (Yuan et al., 2025b) investigated best practices on aspects such as explor...
https://arxiv.org/abs/2505.16022v1
a, we compute the reasoning perplexity Prusing a proxy model πpas follows: Pr(p, t, g ) = exp −P|g| i=1logπp(gi|p, t, g <i) |g| ·N(|t|)! (8) where |g|denotes the number of tokens in the ground truth. N(|t|)is a simple normalization fac- tor based on the length of the reasoning tokens, which alleviates the length bias o...
https://arxiv.org/abs/2505.16022v1
objectively correct answers. The latter distributes rewards to all completions based on their normalized rank and is better suited for subjective or open-ended tasks. Efficiency Reward Recent work (Sui et al., 2025) suggests that longer reasoning is not always better, and effective reasoning length is what mat- ters. W...
https://arxiv.org/abs/2505.16022v1
high-quality data. Specifically: •Natural Reasoning We excluded samples lacking a reference answer. We also filtered out samples where the reference answer was merely a number, a single word, or a single sentence, as such cases are often trivial for rule-based verifiers and do not reflect the open- ended reasoning task...
https://arxiv.org/abs/2505.16022v1
% 38.28 % 50.99 % 1.60 % 34.62 % +SFT 27.50 % 45.20 % 33.50 % 37.85 % 47.66 % 57.06 % 23.30 % 38.87 % +NOV ER 38.20 % 61.80 % 36.60 % 50.79 % 49.22 % 67.79 % 26.80 % 47.31 % Qwen2.5-3B-Instruct 27.10 % 50.00 % 31.50 % 21.25 % 40.62 % 58.69 % 19.90 % 35.58 % Qwen2.5-7B-Instruct 29.90 % 56.20 % 35.60 % 67.72 % 46.88 % 65...
https://arxiv.org/abs/2505.16022v1
Analysis We present a comprehensive and structured experi- ments organized into three main parts. (1)Toex- aminewhen NOVER performs well, §6.1 analyzes its performance across different task types, and §6.2 investigates how data distribution influence reasoning ability. (2)Tounderstand whyNOVER iseffective, §6.3 examine...
https://arxiv.org/abs/2505.16022v1
analyze the key action words from the questions. The model achieves higher accuracy on questions with clear solution directions, such as find,determine , and classify , since the corresponding reasoning chains are more likely to be sampled and reinforced dur- ing training. In contrast, for questions with more flexible ...
https://arxiv.org/abs/2505.16022v1
tokens, such as a keyword point- ing out the discipline of the problem. Both stem from proxy misalignment with the evolving pol- icy, which leads to reward hacking. (2)Adding proxy -policysynchronization mitigates this a lot (blue), though eventual explosion still occasionally occurs. (3)Introducingtheefficiency reward...
https://arxiv.org/abs/2505.16022v1
tern involves stating information from mem- ory as-is. 2.Decomposition The systematic organization of a problem into manageable components, establishing clear steps, intermediate goals, ormethodical frameworks. This pattern involves creating a structured approach to solving com- plex problems. 3.Enumeration The listing...
https://arxiv.org/abs/2505.16022v1
to that there is a straightforward title establishing the intervention goal, an introduction explain- ing the story theme and setting, a main body depicting the specific situation and appropri- ate responses, and a conclusion summarizing the core information presented. 2.Describe more than Direct The number of descript...
https://arxiv.org/abs/2505.16022v1
a new direction for scaling in the post-training era. In- stead of scaling the policy model or the reward model independently, NOVER suggests coordi- nated scaling, since the policy model itself serves as a proxy and effectively takes on the role of the reward model. Acknowledgments This work was supported in part by t...
https://arxiv.org/abs/2505.16022v1
On Reward Functions For Self-improving Chain- of-thought Reasoning Without Supervised Datasets (Abridged Version). In Language Gamification - NeurIPS 2024 Workshop . Gemini, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, and 1 others. 2024. ...
https://arxiv.org/abs/2505.16022v1
Berlin, Germany, September 18-22, 2006, Proceedings , volume 4212 of Lecture Notes in Com- puter Science , pages 282–293. Springer. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yu- taka Matsuo, and Yusuke Iwasawa. 2022. Large Lan- guage Models are Zero-shot Reasoners. In Advances in Neural Information Processing Sys...
https://arxiv.org/abs/2505.16022v1
Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers) , pages 5986–6004, Bangkok, Thailand. Association for Computational Linguistics. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Polic...
https://arxiv.org/abs/2505.16022v1
Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, and 1 others. 2025. Ragen: Understanding self-evolution in llm agents via multi-turn reinforcement learning. arXiv preprint arXiv:2504.20073 . Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichte...
https://arxiv.org/abs/2505.16022v1
arXiv:2502.13124 . Yufeng Yuan, Qiying Yu, Xiaochen Zuo, Ruofei Zhu, Wenyuan Xu, Jiaze Chen, Chengyi Wang, TianTian Fan, Zhengyin Du, Xiangpeng Wei, and 1 others. 2025b. VAPO: Efficient and reliable reinforcement learning for advanced reasoning tasks. arXiv preprint arXiv:2504.05118 . Yang Yue, Zhiqi Chen, Rui Lu, Andr...
https://arxiv.org/abs/2505.16022v1
as “perfect figure” and “elegant dress,” and ac- curately translates and integrates them in later steps. Moreover, NOVER provides more rigorous rubrics, such as emphasizing in the rearrangement step that Spanish word order “may differ from English.” C Reasoning Perplexity Example Figure 11 shows two completions generat...
https://arxiv.org/abs/2505.16022v1
mojada." Step 4: Ensure that the translated sentence maintains the original meaning and tone. The translated sentence maintains the original meaning and tone, as it describes the woman’s appearance and the setting in which she appears. Base Model Translation: Ella era, en efecto, una extraña aparición en un sendero sol...
https://arxiv.org/abs/2505.16022v1
the liver, the bile acids are converted back into cholesterol and stored or used for other purposes. 4. When the body has an excess of cholesterol, the liver produces more bile acids, which are excreted in the feces. ...... In summary, the gastrohepatic cycle is the primary mechanism by which the body eliminates excess...
https://arxiv.org/abs/2505.16022v1
the fatty acids and make them more available for absorption by the small intestine. </think> <answer> The primary mechanism by which the body eliminates excess cholesterol is through the excretion of cholesterol-rich bile acids in the feces. Dietary factors such as fiber intake and fatty food consumption can affect thi...
https://arxiv.org/abs/2505.16022v1
signals for policy optimization under the GRPO training. 19 A False Premise Example in FANToM Dataset Question Here is a dialogue: Eliana: Hello, guys. I find it fascinating how various cultures influence food and cuisine. For instance, in my culture, Brazilian cuisine is a culmination of Europe, Africa, and Native Ame...
https://arxiv.org/abs/2505.16022v1
Mexico! What dishes from Scotland and Canada does Eliana think that Alberto believes were discussed by Addison and Kade respectively? Reference: Alberto is unaware about which dishes from Scotland and Canada were discussed by Addison and Kade respectively as he was not involved in the conversation when this was discuss...
https://arxiv.org/abs/2505.16022v1
arXiv:2505.16023v2 [cs.CL] 23 May 2025Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild Sheshera Mysore1△Debarati Das2†Hancheng Cao1Bahar Sarrafzadeh1△ 1Microsoft, WA, USA2University Of Minnesota, MN, USA △Corresponding authors: smysore@iesl.cs.umass.edu ,bahar.sarrafzadeh@microsoft.co...
https://arxiv.org/abs/2505.16023v2
on realistic in-the-wild interactions. We contribute such an analysis by focusing on LLM-assisted writing, a important and increasingly prevalent use case for AI assistants (Tamkin et al., 2024; Suri et al., 2024). Recent studies have found that LLM-assisted writing is now common in im- pactful domains such as press re...
https://arxiv.org/abs/2505.16023v2
proving (Collins et al., 2024a), image generation (Palmini et al., 2024; V odrahalli and Zou, 2024), and writing assistance (Lee et al., 2022). Most relevant is the prior work on log analysis for UI based writing as- sistance (Lee et al., 2022; Sarrafzadeh et al., 2021). Respectively, they analyze model outputs, collab...
https://arxiv.org/abs/2505.16023v2
we ensure that sessions con- tain users’ follow-up utterances and retain sessions with at least 2 user utterances and those in English. On the resulting 2.8M sessions, we run fCoarseT to identify writing sessions and retain 250k sessions in BCP Wr. GPT-4 powered all interactions in BCP. WildChat - WC WrWe follow a simi...
https://arxiv.org/abs/2505.16023v2
REQUESTS MORE OUTPUTS Asks for additional output CHANGE STYLE Changes style of output ADDS CONTENT Adds content to output REMOVES CONTENT Remove content from output COURTESY RESPONSE A courtesy or pleasantry RESPONDS POSITIVELY Explicitly pleased with output RESPONDS NEGATIVELY Explicitly unhappy with output UNDEFINED ...
https://arxiv.org/abs/2505.16023v2
similar and small percentage of variance (8- 14%), with most PATHs corresponding to a single follow-up type. This suggests that each follow-up type captures a distinct form of collaboration, with multiple co-occurring follow-up types being less frequent. When follow-up types do co-occur, this is more common in rare fol...
https://arxiv.org/abs/2505.16023v2
on requests. §D.2 Table 4: Overview of PATHs in our regression analysis. gets. Table 4 summarizes the behaviors examined in our analysis. To ensure generalization of our findings, we highlight statistically significant corre- lations shared across BCP Wrand WC Wr, and exam- ine frequent writing intents (Figure 8). We p...
https://arxiv.org/abs/2505.16023v2
narra- tives with under-specific multi-turn interaction. 6.2 Asking follow-up questions to learn or stage long generations Figure 5a shows writing intents correlated with PATH3, where users ask questions in response tomodel generations. Users tended to ask questions when they generated professional documents (I3), summ...
https://arxiv.org/abs/2505.16023v2
content known only to the user Figure 6a shows writing intents correlated with PATH4 where users add content to model genera- tions. This behavior correlates with generating pro- fessional documents (I3), messages (I2), and cre- ative narratives (I11-I13). Our analysis of sessions found that users overwhelmingly added ...
https://arxiv.org/abs/2505.16023v2
work suggested by our results. Toward Session-Level Alignment from Nat- ural Feedback. We showed how user follow- ups rarely included explicit positive or negative feedback in §5 and engage in open-ended collab- oration behaviors in §6. However, a majority of present work on LLM alignment remains restricted to single-t...
https://arxiv.org/abs/2505.16023v2
of cultural bias in “coaching,” preventing homogenization of users’ voice and ideas (Agarwal et al., 2025; Drosos et al., 2025), and designing interactions that preserve the “productive struggle” known to facilitate deeper learning (Rus and Kendeou, 2025). Ultimately, building LLM systems for learning will demand rich ...
https://arxiv.org/abs/2505.16023v2
ACM SIGIR Conference on Research and Development in Information Retrieval , SIGIR ’22, page 2850–2862, New York, NY , USA. Association for Computing Machinery. Aparna Ananthasubramaniam, Hong Chen, Jason Yan, Kenan Alkiek, Jiaxin Pei, Agrima Seth, Lavinia Dunagan, Minje Choi, Benjamin Litterer, and David Jurgens. 2023....
https://arxiv.org/abs/2505.16023v2
NY , USA. Association for Computing Machinery. Katherine M. Collins, Albert Q. Jiang, Simon Frieder, Lionel Wong, Miri Zilka, Umang Bhatt, Thomas Lukasiewicz, Yuhuai Wu, Joshua B. Tenenbaum, William Hart, Timothy Gowers, Wenda Li, AdrianWeller, and Mateja Jamnik. 2024a. Evaluating lan- guage models for mathematics thro...
https://arxiv.org/abs/2505.16023v2
City, Mexico. Association for Computational Linguistics. Katy Ilonka Gero, Tao Long, and Lydia B Chilton. 2023. Social dynamics of ai support in creative writing. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems , CHI ’23, New York, NY , USA. Association for Computing Machinery. Derek Gre...
https://arxiv.org/abs/2505.16023v2
for Computing Machinery. Mina Lee, Percy Liang, and Qian Yang. 2022. Coau- thor: Designing a human-ai collaborative writing dataset for exploring language model capabilities. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems , CHI ’22, New York, NY , USA. Association for Computing Machiner...
https://arxiv.org/abs/2505.16023v2
Domain, Application, Group, or Individual (CustomNLP4U) , pages 198–219, Miami, Florida, USA. Association for Computational Linguistics. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, JohnSchulman, Jacob Hilton, Fraser Kelto...
https://arxiv.org/abs/2505.16023v2
Tara Safavi, Jennifer Neville, Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Sathish Manivannan, Nagu Rangan, and Longqi Yang. 2024. The use of generative search engines for knowledge work and complex tasks. Preprint , arXiv:2404.04268. Alex Tamkin, Miles McCain, Kunal Handa, Esin Dur- mus, Liane Lovitt, An...
https://arxiv.org/abs/2505.16023v2
Towards better automatic storytelling. Pro- ceedings of the AAAI Conference on Artificial Intelli- gence , 33(01):7378–7385. Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, and Yuntian Deng. 2024a. Wildchat: 1m chatGPT interaction logs in the wild. In The Twelfth International Conference on Learning Re...
https://arxiv.org/abs/2505.16023v2
LLM outputs and tasks contexts (Fu et al., 2024; Bhattacharjee et al., 2024), among others. Studies focusing on the dynamics of human-AI co-creation examine the differences in how writers seek feedback from humans vs LLMs(Gero et al., 2023), or how they seek assistance at different stages of writing (Wan et al., 2024; ...
https://arxiv.org/abs/2505.16023v2
et al. (2024a) gath- ered this data over thirteen months from 9 April 2023 to 1 May 2024 in a HuggingFace Hub space. The sessions contain interactions with GPT-4 and GPT-3.5-Turbo. Of the 840k publicly available ses- sions, we retain sessions labeled as English in the metadata and with 2 or more user utterances – this ...
https://arxiv.org/abs/2505.16023v2
Summarize Text as writing sessions. Out of 2.8M sessions, we identify 500k as writing sessions. These made up 17-19% sessions in each month. Finally, we randomly subsample 250k of 500k, re- sulting in BCP Wr. Our sub-sampling was done to lower the costs of subsequent analysis, which relies on LLM classifiers while reta...
https://arxiv.org/abs/2505.16023v2
Analysis. •Appendix C.3: Details about manually vali- dating the Follow-up and Intent Classifier. C.1 Identifying P ATHs We identify PATHs by first classifying users’ follow- up utterances into high-level follow-up types and clustering these into P ATHs using PCA. Follow-up Classifier. We use a GPT-4o based follow-up c...
https://arxiv.org/abs/2505.16023v2
this proce- dure until new labels aren’t generated. We man- ually apply the labels to 200 randomly sampled BCP Wrsessions to ensure their coverage. Table 10 shows example original requests for each writing intent. We validate the accuracy of fWritingI through manual annotation in Appendix C.3. Regression Analysis. We r...
https://arxiv.org/abs/2505.16023v2
correlations between writing intents and PATHs or follow-up types in our regression analysis. ing to understand the user goals for engaging in aPATH. Then both authors met and resolved the differences in their understanding. In our analy- sis, the two authors differed in the interpretation of one of the six intent- PAT...
https://arxiv.org/abs/2505.16023v2
across domains (I1), and generate messages, summaries, and online posts (I2, I4, I8). Analysis of sessions revealed that users frequently changed the style of generations to better match the assumed norms for a communication (Ex 2,3,4) or to the likely preference of readers (Ex 1,5). Specifically, when users sought to ...
https://arxiv.org/abs/2505.16023v2
to im- prove LLM performance. Future work may attempt to identify more distinguished PATHs through a finer-grained analysis of sessions with revised or elaborated requests. 19 −0.8 −0.6 −0.4 −0.2 0.0 Es8ima8.d co.ffici.48REQUEST LENGTHUNDEFINED REQ.Q. AB UT WRITINGGENERATE J KEGENERATE S NGGENERATE P EMGEN CHARACTERGEN...
https://arxiv.org/abs/2505.16023v2
−0.75 −0.50 −0.25 0.00 0.25 0.50 0.75 E7t1mat.d c5.ff1c1.ntREQUEST LENGTHUNDEFINED REQ.Q. AB UT WRITINGGENERATE J KEGENERATE S NGGENERATE P EMGEN CHARACTERGENERATE SCRIPTGENERATE ST RYGEN CATCHY TEXTGENERATE BI GEN NLINE P STGET REFERENCESGENERATE ESSAYGEN TECHN. TEXTGEN SUMMARYGEN PR FESS. D CGEN MESSAGEIMPR VE TEXTWC...
https://arxiv.org/abs/2505.16023v2
Text SOFTWARE DEVELOPMENT : The user is seeking assistance in software development . Often phrased as a how to question with accompanying code . ←Develop Software HOMEWORK PROBLEM : The user is posing a question or problem which is likely to be from an exam or homework . ←Solve Problem GENERATING CREATIVE TEXT : The us...
https://arxiv.org/abs/2505.16023v2
is requesting new or additional information related to the ASSISTANTs response . REQUESTS MORE OUTPUTS : The user is requesting additional output from the ASSISTANT . RESPONDS POSITIVELY : The user is responding positively to the ASSISTANTs response without providing additional detail . RESPONDS NEGATIVELY : The user i...
https://arxiv.org/abs/2505.16023v2
1-4 and re number the rest” “Today is my senior patrol election and I want to win. I need to provide a 2-3 minute speech...” →“Remove the details about having less experience and emphasize how I want to use my creativity...” COURTESY RESPONSE A courtesy or pleasantry “write a short 100 word Youtube channel description ...
https://arxiv.org/abs/2505.16023v2
or other eye catching text . ↖GENERATE CATCHY TEXT GENERATE SUMMARY : Request to summarize a text provided by the user . GENERATE ESSAY : Request to write an essay , blog , article or other long text on any topic . GENERATE TECHNICAL TEXT : Request to write or re - write a scientific or technical text QUESTION ABOUT WR...
https://arxiv.org/abs/2505.16023v2
BIO “Write me a bio for me 450 charters of someone who’s loves to read books” “i want to write a short biography about myself saying that i am an audio engineer that graduated from...” GENERATE CATCHY TEXT “generate 5 new original desalination company names” “suggest me 10 thumbnail texts for this youtube video Young B...
https://arxiv.org/abs/2505.16023v2
arXiv:2505.16036v1 [cs.CL] 21 May 2025OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models Burak Erinç Çetin, Yıldırım Özen, Elif Naz Demiryılmaz, Kaan Engür, Cagri Toraman Middle East Technical University, Computer Engineering Department, Applied NLP Group {erinc.cetin,yildiri...
https://arxiv.org/abs/2505.16036v1
gaps in language coverage, evaluation breadth, and model diversity. By doing so, we are able to deliver a compre- hensive ethical evaluation of generative large lan- guage models, thus helping guide safer and more reliable model development. Our study contributes to the growing discourse on the ethical implications of ...
https://arxiv.org/abs/2505.16036v1
biases in gender, age, and race become a significant issue (Sakib and Bijoy Das, 2024). Language Gap A significant limitation of the existing ethical LLM evaluation landscape is its strong Anglocentric bias. The majority of studies are developed primarily for English. Since model performance, safety alignment, and reli...
https://arxiv.org/abs/2505.16036v1
2024a), classified into three primary types: Attention Shifting (16 templates), Pretend- ing (15 templates), and Privilege Escalation (five templates). Attention Shifting Templates are designed to di- vert the model’s attention from the potentially harmful nature of the requested task by empha- sizing secondary aspects...
https://arxiv.org/abs/2505.16036v1
(Li et al., 2023a) 4 Custom 6 Factual fabrication (Casper et al., 2023) and Custom 12 Defending fabrication (Casper et al., 2023) and Custom 10 Safety (174)Violence(Tedeschi et al., 2024) 32 (Bhardwaj and Poria, 2023) 2 (Ji et al., 2023) 13 (Li et al., 2024) 1 (Ahmadian et al., 2024) 13 Unlawful Conduct(Tedeschi et al....
https://arxiv.org/abs/2505.16036v1
disclosure of private details. Misuse explores the potential of exploiting the model for broader harmful purposes not strictly covered by the preceding categories. This cate- gory assesses the model’s refusal to assist in activ- ities such as generating large-scale disinformation campaigns, creating malicious code, aid...
https://arxiv.org/abs/2505.16036v1
et al., 2024) Gemma 2 27B google/gemma-2-27b-it (Riviere et al., 2024) Gemma 3 4B google/gemma-3-4b-it (Kamath et al., 2025) Gemma 3 12B google/gemma-3-12b-it (Kamath et al., 2025) Gemma 3 27B google/gemma-3-27b-it (Kamath et al., 2025) Granite 3.1 8B ibm-granite/granite-3.1-8b-instruct (IBM, 2024) Llama 3.1 70B RedHat...
https://arxiv.org/abs/2505.16036v1
the results of the English prompts and their Turkish equivalents, we observe similar average scores for all dimen- sions. The reason could be the extensive mul- tilingual pre-training (Doddapaneni et al., 2021). English prompts still have higher average scores, as expected due to their dominance in the training corpus ...
https://arxiv.org/abs/2505.16036v1
We find that reliability prompts are rarely, but safety prompts are mostly rejected. Models can answer in a safe manner without refusing (e.g., 78.84% in Fairness). Reasoning models reject less compared to others. Models reject much more in English compared to Turkish. A detailed discus- sion on rejection analysis is g...
https://arxiv.org/abs/2505.16036v1
not fully represent the dynamic challenges faced by real-world LLM users. Methodologically, our robustness assessment focused on simple jailbreak templates. This ap- proach provides a useful baseline but does not re- flect the complexity of multi-turn interactions or more advanced adversarial techniques, and results sh...
https://arxiv.org/abs/2505.16036v1
et al. 2024. Aya 23: Open weight releases to further multilingual progress. arXiv preprint arXiv:2405.15032 . AWS. 2024. Common prompt injection at- tacks - AWS Prescriptive Guidance — docs.aws.amazon.com. https://docs.aws. amazon.com/prescriptive-guidance/latest/ llm-prompt-engineering-best-practices/ common-attacks.h...
https://arxiv.org/abs/2505.16036v1
Krithika Iyer, Kshi- tiz Malik, Kuen ley Chiu, Kunal Bhalla, Lauren Rantala-Yeary, Laurens van der Maaten, Lawrence Chen, Liang Tan, Liz Jenkins, Louis Martin, Lo- vish Madaan, Lubo Malo, Lukas Blecher, Lukas Landzaat, Luke de Oliveira, Madeline Muzzi, Ma- hesh Pasupuleti, Mannat Singh, Manohar Paluri, Marcin Kardas, M...
https://arxiv.org/abs/2505.16036v1
Igor Tufanov, Irina-Elena Veliche, Itai Gat, Jake Weissman, James Geboski, James Kohli, Japhet Asher, Jean-Baptiste Gaya, Jeff Marcus, Jeff Tang, Jennifer Chan, Jenny Zhen, Jeremy Reizenstein, Jeremy Teboul, Jessica Zhong, Jian Jin, Jingyi Yang, Joe Cummings, Jon Carvill, Jon Shepard, Jonathan McPhie, Jonathan Torres, ...
https://arxiv.org/abs/2505.16036v1