text string | source string |
|---|---|
- It’s like watching a live-action superhero show, but with more keyboards and less popcorn. - Dota 2 is a game that will make you feel like a powerful wizard, without the risk of turning into a toad. - So grab your magic staff and get ready to battle it out in the Aeon of Strife! The model associates a "zany" response... | https://arxiv.org/abs/2505.16927v1 |
we acknowledge the role that clustering plays in making informed assessments over the constitution; as such, constrained STaPLe is more controllable in comparison to the unconstrained version. While this reintroduces human oversight to balance performance with safety, it would add minimal human labor overhead, as judgi... | https://arxiv.org/abs/2505.16927v1 |
pairs (chosen- rejected) over helpfulness and harmlessness as described in Bai et al. (2022a). HH-RLHF is available under the MIT license. •UltraFeedback (Cui et al., 2024): this dataset consists of 64k prompts; for each prompt, responses are sampled from four different language models. For each response, Likert-scale ... | https://arxiv.org/abs/2505.16927v1 |
arXiv:2505.16931v1 [cs.CL] 22 May 2025PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues Matthew Zent Digory Smith Simon Woodhead Eedi matthew.zent@eedi.co.uk Abstract Personally identifiable information (PII) anonymization is a high-stakes task that poses a barrier to many open-... | https://arxiv.org/abs/2505.16931v1 |
not suitable for all types of analysis (e.g., qualitative), and is susceptible to de-anonymization attacks (Carlini et al., 2021). Ob- fuscating PII typically relies on automated recog- nition (Buchh, 2024; Bosch et al., 2020; Holmes et al., 2023; Singhal et al., 2024) or manual label- ing (Miller and DiCerbo, 2024), b... | https://arxiv.org/abs/2505.16931v1 |
surrogate replacement. 2.1.2 Anonymization The anonymization step utilizes labeled spans to generate surrogate replacements under the as- sumption that the content of non-PII spans can be changed without impacting dataset quality, so long as the same name/location/etc. is consistent throughout the conversation or docum... | https://arxiv.org/abs/2505.16931v1 |
The associated text-based metadata was extracted using the Mathpix API v3, then labeled and validated by tutors. 4Sexual, sexual/minors, harassment, harass- ment/threatening, hate, hate/threatening, illicit, illicit/violent, self-harm, self-harm/intent, self-harm/instructions, violence, and violence/graphic.tizes diver... | https://arxiv.org/abs/2505.16931v1 |
1:1 tutoring datasets. Uptake is modeled using Demszky et al. (2021). PIIvot had little to no effect on text-based metrics. Label Set Source Precision Recall F1 DialoguesPIIvot 0.984 0.984 0.984 Annotators 0.993 0.995 0.994 QuestionsPIIvot 0.991 0.699 0.820 Annotators 0.997 0.997 0.997 Table 2: Micro-averaged metrics f... | https://arxiv.org/abs/2505.16931v1 |
cance of replaced content and mitigate this limita- tion in new contexts. Recent work demonstrates the potential of incorporating LLM-generated feedback to improve LLM summarization tasks (Song et al., 2025), suggesting a promising direction for PIIvot anonymization feedback. Related, the framework relies on an effecti... | https://arxiv.org/abs/2505.16931v1 |
applied data mini- mization principles to student data, and outline the following recommendations for appropriate sec- ondary use. In accordance with Eedi’s privacy pol- icy, QATD is released for non-commercial research (under cc-by-nc-sa-4.0) aimed at improving stu- dent learning outcomes, including, but not limited t... | https://arxiv.org/abs/2505.16931v1 |
Cha- troom Corpus. In Proceedings of the 9th Workshop on NLP for Computer Assisted Language Learning , pages 10–20, Gothenburg, Sweden. LiU Electronic Press. Michela Carlana and Eliana La Ferrara. 2024. Apart but connected: Online tutoring, cognitive outcomes, and soft skills. Technical report, National Bureau of Econo... | https://arxiv.org/abs/2505.16931v1 |
John Wiley & Sons, Ltd. Shouling Ji, Prateek Mittal, and Raheem Beyah. 2017. Graph Data Anonymization, De-Anonymization At- tacks, and De-Anonymizability Quantification: A Survey. IEEE Communications Surveys & Tutorials , 19(2):1305–1326. Wenda Li, Lei Yu, Yuhuai Wu, and Lawrence C. Paul- son. 2021. IsarStep: a Benchma... | https://arxiv.org/abs/2505.16931v1 |
Enhancing mathematical capabilities through ChatGPT and similar generative artificial intelligence: Roles and challenges in solving mathe- matical problems. Available at SSRN 4603237 . Aniruddha Sen, Christine Task, Dhruv Kapur, Gary Howarth, and Karan Bhagat. 2024. Diverse commu- nity data for benchmarking data privac... | https://arxiv.org/abs/2505.16931v1 |
an independent batch of 66,059 tu- tor/student messages took place from May to Au- gust 2024 by paid employees of Eedi. The first and second authors (US/UK/Male) and 4 expert tutors (UK/Female) participated in this annotation process; tutors annotated messages while not ac- tively helping students. We used the open-sou... | https://arxiv.org/abs/2505.16931v1 |
AdamW ,raw + synthetic vs. raw data, and windowing vs. non-windowing. For the synthetic data, 20 PII-rich synthetic student- tutor conversations were manually created by the authors to augment the training and validation data with examples of imbalanced classes. For the win- dowing condition, model inputs include the p... | https://arxiv.org/abs/2505.16931v1 |
arXiv:2505.16932v1 [cs.LG] 22 May 2025The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm Noah Amsel∗David Persson†Christopher Musco‡Robert Gower§ May 23, 2025 Abstract Computing the polar decomposition and the related matrix sign function, has been a well-studied problem in numer... | https://arxiv.org/abs/2505.16932v1 |
. . . . . . . 13 4.5 The algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 5 Numerical experiments 15 5.1 Convergence of Polar Express . . . . . . . . . . . . . . . . . . . . . . . . . 15 5.2 Training GPT-2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 A Proof o... | https://arxiv.org/abs/2505.16932v1 |
learning rate. The final best validation loss for each method, in reverse order was adamw : 4.197, muon-Jordan : 3.639, muon-You : 3.629 and muon-PolarExp : 3.588. 1.1 The Muon Method Muon has recently gained popularity for training large language models, often outperforming state-of-the-art adaptive gradient methods l... | https://arxiv.org/abs/2505.16932v1 |
Newton-Schulz method constructs a sequence of approximations Xt≈polar (M) as follows: X0=M/∥M∥F Xt+1=3 2Xt−1 2XtX⊤ tXt (2) At each iteration, this rule effectively applies the cubic polynomial p(x) =3 2x−1 2x3to the singular values of Xt. It is well-known that the scalar fixed point iteration xt+1=p(xt) converges to si... | https://arxiv.org/abs/2505.16932v1 |
algorithm (Figure 1), showing that it consistently improves the training of GPT-2 language models on 1 billion tokens of the Fineweb dataset [3]. Notation. We let∥M∥Fand∥M∥2denote the Frobenius norm and spectral norm (largest singular value) of a matrix M, respectively. We denote the spectrum (set of singular values) b... | https://arxiv.org/abs/2505.16932v1 |
Newton is also a Pad´ e method, though a rational rather than polynomial one. In fact, given a odd degree 2 qn+ 1 for the numerator and an even degree 2 qdfor the denominator, there is a unique rational function that matches the value and first qn+qdderivatives of sign(x) atx=±1. This directly yields a Pad´ e method fo... | https://arxiv.org/abs/2505.16932v1 |
It is shown that these rationals have remarkable convergence properties for any q. For even faster convergence than QDWH, the zolo-pd method chooses q= 17 [ 34]. Finally, these methods admit the same QR-based implementation trick as QDWH. In this paper, we adopt the paradigm of zolo-pd [ 34] but with polynomials rather... | https://arxiv.org/abs/2505.16932v1 |
i)Linear combinations: given scalars β,γ∈Rand matrices BandC, compute βB+γC, ii) Matrix-matrix products: compute BC. While both these computational primitives are well-suited for parallel computing en- vironments, matrix-matrix products come at a higher computational cost than linear combinations. Therefore, our method... | https://arxiv.org/abs/2505.16932v1 |
the choice of polynomials from the previous iterations. For the first iteration, we choosep1so as to map the interval [ ℓ,u] as close to 1 as possible. That is, it minimizes maxx∈[ℓ,u]|1−p1(x)|. The image of p1will be a new interval [ ℓ2,u2], where ℓ2= min x∈[ℓ,u]p1(x)u2= max x∈[ℓ,u]p1(x) (9) We now pick p2to map the i... | https://arxiv.org/abs/2505.16932v1 |
applying the iterative procedure of (6), the final iterate XTwill satisfy the following error bound ∥polar(M)−XT∥2=∥polar(M)−p⋆(M)∥2≤1−ℓT+1. (13) From optimality guarantee of Theorem 4.1, we know that our method converges at least as fast as the Newton-Schulz iteration of the same degree. Combining this fact with an ex... | https://arxiv.org/abs/2505.16932v1 |
approximants, and the function we wish to approximate is a constant. For d= 3, we can actually derive an explicit, closed form solution to (15) using the Equioscillation Theorem. Up to rescaling, the optimal polynomial turns out to be the same one derived in Chen and Chow by different means [ 12]. For degree d= 5, we p... | https://arxiv.org/abs/2505.16932v1 |
u= 1. This rescaling has no effect on the error of our method. It is difficult to efficiently find a good lower bound on the smallest singular value, so we are forced to guess. Fortunately, the consequences of a bad guess are not severe. As discussed above, the method will eventually converge for any ℓ∈(0,u], and even ... | https://arxiv.org/abs/2505.16932v1 |
mapped down to ℓt+1. It so hap- pens that this non-monotonicity—even of a single singular value at a single iteration— causes loss of precision. That is, problems occur if pt(σi) σi≪max x∈[σmin,σmax]pt(x) σmax, where 0≤σmin≤σi≤σmaxare singular values of Xt[35]. (In the extreme case, ifpt(σi)<0, theith singular vector w... | https://arxiv.org/abs/2505.16932v1 |
the input matrix is known exactly. We generate a random matrix whose singular values are evenly spaced on a logarithmic scale between 10−6and 1. The right and 15 0 5 10 15 20 25 Iteration10−310−210−1100Spectral ErrorSynthetic Matrix σmin/σmax= 10−6 2 4 6 8 10 Iteration0.000.250.500.751.00 GPT-2 Gradient Layer 4 mlp.c p... | https://arxiv.org/abs/2505.16932v1 |
products is T(d+ 1)/2, wheredis the degree (3 for Chen & Chow; 5 for all others) and Tis the number of iterations. the number of matrix-matrix products performed by each method instead the number of iterations. We find that Polar Express can once again dominate the other methods across iterations. Chen and Chow’s metho... | https://arxiv.org/abs/2505.16932v1 |
Vincent, and Anirudh Goyal. Fineweb: Learning language models with high quality web data. In NeurIPS Datasets and Benchmarks Track , 2023. URL: https://arxiv.org/abs/2306.03061 . 18 [4]Michele Benzi and Ru Huang. Some matrix properties preserved by generalized matrix functions. Spec. Matrices , 7:27–37, 2019. doi:10.15... | https://arxiv.org/abs/2505.16932v1 |
Trans. Signal Process. , 61(4):883–894, 2013. doi:10.1109/TSP.2012.2226167 . [25] Andrej Karpathy. char-rnn. https://github.com/karpathy/char-rnn , 2015. [26]Charles Kenney and Alan J. Laub. Rational iterative methods for the matrix sign function. SIAM J. Matrix Anal. Appl. , 12(2):273–291, 1991. doi:10.1137/0612020 . ... | https://arxiv.org/abs/2505.16932v1 |
N. Trefethen. Approximation theory and approximation practice . Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA, extended edition, 2020. [46]Greg Yang, James B. Simon, and Jeremy Bernstein. A spectral condition for feature learning, 2024. URL: https://arxiv.org/abs/2310.17813 ,arXiv:2310.17813 .... | https://arxiv.org/abs/2505.16932v1 |
a point can be both a stationary point and an endpoint we have q+ 2≤nend+nstat. However, nend≤2 andnstat≤q, which follows from the previous paragraph where we showed that there are at most qstationary points ofe(x) in [ℓ,u]. Sonend+nstat≤q+ 2, and consequently we must have nend= 2 and nstat=q, as required. Step 2:x=ℓis... | https://arxiv.org/abs/2505.16932v1 |
x∈[ℓ,u]|1−cf(x)|= max{1−ca,cb−1}=b−a a+b. Recall by our inductive hypothesis, we have max x∈[ℓ,u]|1−g(x)|= 1−ℓT=uT−1 where the second equality holds by (11). It follows that a b>ℓT uT ⇔a b>ℓT 2−ℓT ⇔ℓT<2a a+b ⇔1−ℓT>b−a a+b ⇔max x∈[ℓ,u]|1−g(x)|>max x∈[ℓ,u]|1−cf(x)|, which leads to a contradiction to our inductive hypothe... | https://arxiv.org/abs/2505.16932v1 |
larger dfinding closed form expressions for optimal approximations from Podd dbecomes challenging. In fact, to the best of our knowledge the optimal approximation is not known for d≥5. However, we can approximate the optimal polynomial using the Remez algorithm. Letd= 2q+ 1. Recall that from Lemma A.1 the optimal polyn... | https://arxiv.org/abs/2505.16932v1 |
all equioscillation points x0,x1,x2,x3must converge to u. For general d= 2q+ 1, the polynomial will converge to ( x/ℓ)h(1−(x/ℓ)2) whereh∈Pq is the [q/0] Pad´ e approximant to (1 −x)1/2[26]. In fact, this polynomial is extremely close to the optimal polynomial for sufficiently large ℓ. To see this, let p⋆be the optimal ... | https://arxiv.org/abs/2505.16932v1 |
simultaneously. For simplicity, we treat only thek= 1 case here. Assume that Mis normalized to ∥M∥F= 1 and let z=˜σ1 be the lower bound produced by subspace iteration (which reduces to the power method in this case). Then (21) givesσ1∈[z,1] andσ2,...,σn≤√ 1−z2. Assume that these intervals do not overlap, that is,√ 1−z2... | https://arxiv.org/abs/2505.16932v1 |
2α/parenrightig ·n3operations. This process could be repeated for each iteration p1,...,pT. Notice that if we instead computedh(XX⊤)X, the result would be the same but the cost would be higher. A major drawback of this naive approach is that it has a strong dependence on α, since two rectangular matrix multiplications... | https://arxiv.org/abs/2505.16932v1 |
3. While this technique may already be applicable in float32 or for architectures whose weight matrices have larger aspect rations, more work is needed to make it practical for general deep learning applications. If these problems can be mitigated, the speed afforded by Algorithm 3 suggests a potentially beneficial cha... | https://arxiv.org/abs/2505.16932v1 |
sqrt (( -3*b + np. array ([ -1 , 1]) * sqrt (9* b**2 - 20* a*c)) / (10* c)) return float (a), float (b), float (c) def optimal_composition (l, num_iters , cushion =0.02407327424182761) : u = 1 coefficients = [] for _ in range ( num_iters ): a, b, c = optimal_quintic (max (l, cushion *u), u) # Due to cushioning , this m... | https://arxiv.org/abs/2505.16932v1 |
arXiv:2505.16933v1 [cs.LG] 22 May 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning Zebin You1,2,3, Shen Nie1,2,3, Xiaolu Zhang4, Jun Hu4, Jun Zhou4, Zhiwu Lu1,2,3,Ji-Rong Wen1,2,3,Chongxuan Li1,2,3∗ 1Gaoling School of AI, Renmin University of China2Beijing Key Laboratory of Research on Large ... | https://arxiv.org/abs/2505.16933v1 |
naturally raises a key research question: Can an purely diffuision based MLLM (both training and sampling) achieve performance compared to autoregressive-based models? In this paper, we explore how to effectively extend large language diffusion models to encompass strong multimodal understanding capabilities, focusing ... | https://arxiv.org/abs/2505.16933v1 |
let x0= [xi]N i=1represent a sentence comprising N tokens, and let [M]denote a special mask token. LLaDA defines a model distribution pθ(x0)through a forward and a reverse process. In the forward process, LLaDA first samples a time step tuniformly from the interval [0,1]. Subsequently, each token in x0is replaced by [M... | https://arxiv.org/abs/2505.16933v1 |
explicitly shown). (a) Autoregressive Training: Given image features and the input prompt, autoregressive models are trained to predict the response through next-token prediction. (b) LLaDA-V’s Training: Image features and the input prompt remain unmasked, while only the response is randomly masked. (c) LLaDA-V’s Infer... | https://arxiv.org/abs/2505.16933v1 |
diffusion models. For the remasking strategy, rather than using standard random selection, we primarily adopt LLaDA’s [ 42]low-confidence strategy, which preferentially re-masks low-confidence predictions while preserving high-confidence ones. We choose this approach based on its consistently demonstrated improvements ... | https://arxiv.org/abs/2505.16933v1 |
17,18]. Consequently, its performance falls behind Qwen2.5-7B- Instruct [ 19] and is marginally inferior to LLaMA3-8B-Instruct [ 18]. For a fair comparison between 5 Table 1: Training Settings. Here M-SI and M-OV represent the single image data and onevision data of MAmmoTH [ 55], while VW represents the data of Visual... | https://arxiv.org/abs/2505.16933v1 |
in Fig. 3, we observe two key findings: First, LLaDA-V’s performance consistently improves with increasing training data, demonstrating that LLaDA-V benefits from data scalabil- ity. Second, despite using a slightly weaker language tower, LLaDA-V shows superior scalability compared to LLaMA3-V on multidisciplinary know... | https://arxiv.org/abs/2505.16933v1 |
against three different model architectures—autoregressive, hybrid autoregressive-diffusion, and pure diffusion models—across a diverse set of 18 benchmarks (detailed results in Tab. 2 and Tab. 3). These benchmarks encompass areas such as multidisciplinary knowledge, mathematical reasoning, chart/document understanding... | https://arxiv.org/abs/2505.16933v1 |
further fine-tune the entire model on the LLaV A-NeXT dataset [54]. Training hyperparameter details are provided in Tab. 1. We consider two attention mask strategies: dialogue causal and no mask (i.e., bidirectional attention). In the dialogue causal approach, earlier dialogue turns cannot attend to later turns. Conver... | https://arxiv.org/abs/2505.16933v1 |
Multimodal Large Language Model (MLLM) for both training and sampling, which builds upon the visual instruction tuning framework [ 1] and the large language diffusion model [ 42]. LLaDA-V demonstrates superior performance among hybrid autoregressive-diffusion and purely diffsion-based model. Besides, LLaDA-V achieve be... | https://arxiv.org/abs/2505.16933v1 |
Z. Yan, Y . He, J. Yu, X. Zeng, C. Wang, C. Ma, H. Huang, J. Gao et al. , “Internvideo2. 5: Empowering video mllms with long and rich context modeling,” arXiv preprint arXiv:2501.12386 , 2025. [11] L. Chen, X. Wei, J. Li, X. Dong, P. Zhang, Y . Zang, Z. Chen, H. Duan, Z. Tang, L. Yuan et al. , “Sharegpt4video: Improvin... | https://arxiv.org/abs/2505.16933v1 |
and multinomial diffusion: Learning categorical distributions,” NeurIPS , vol. 34, pp. 12 454–12 465, 2021. [26] J. Austin, D. D. Johnson, J. Ho, D. Tarlow, and R. van den Berg, “Structured denoising diffusion models in discrete state-spaces,” in Advances in Neural Information Processing Systems , 2021. [27] F. Bao, S.... | https://arxiv.org/abs/2505.16933v1 |
2024. [41] J. Ou, S. Nie, K. Xue, F. Zhu, J. Sun, Z. Li, and C. Li, “Your absorbing discrete diffusion secretly models the conditional distributions of clean data,” arXiv preprint arXiv:2406.03736 , 2024. [42] S. Nie, F. Zhu, Z. You, X. Zhang, J. Ou, J. Hu, J. Zhou, Y . Lin, J.-R. Wen, and C. Li, “Large language diffus... | https://arxiv.org/abs/2505.16933v1 |
, 2024. [56] Y . Jia, J. Li, X. Yue, B. Li, P. Nie, K. Zou, and W. Chen, “Visualwebinstruct: Scaling up multimodal instruction data through web search,” arXiv preprint arXiv:2503.10582 , 2025. [57] Q. Team, “Qwen3: Think deeper, act faster,” 2025, https://qwenlm.github.io/blog/qwen3/. [Online]. Available: https://qwenl... | https://arxiv.org/abs/2505.16933v1 |
The Netherlands, October 11–14, 2016, Proceedings, Part IV 14 . Springer, 2016, pp. 235–251. [70] A. Masry, D. X. Long, J. Q. Tan, S. Joty, and E. Hoque, “Chartqa: A benchmark for question answering about charts with visual and logical reasoning,” arXiv preprint arXiv:2203.10244 , 2022. 13 [71] M. Mathew, D. Karatzas, ... | https://arxiv.org/abs/2505.16933v1 |
preprint arXiv:2409.18869 , 2024. [84] H. Laurençon, L. Tronchon, M. Cord, and V . Sanh, “What matters when building vision- language models?” Advances in Neural Information Processing Systems , vol. 37, pp. 87 874– 87 907, 2024. [85] X. Li, J. Thickstun, I. Gulrajani, P. S. Liang, and T. B. Hashimoto, “Diffusion-lm im... | https://arxiv.org/abs/2505.16933v1 |
Salimans, “Autoregressive diffusion models,” arXiv preprint arXiv:2110.02037 , 2021. [102] C. Meng, K. Choi, J. Song, and S. Ermon, “Concrete score matching: Generalized score matching for discrete data,” Advances in Neural Information Processing Systems , vol. 35, pp. 34 532–34 545, 2022. [103] M. Reid, V . J. Hellend... | https://arxiv.org/abs/2505.16933v1 |
. . . . . . . . . . . . . . . . . . . . . . . 5 4 Experiment 5 4.1 Experimental Settings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 4.2 Data Scalability of LLaDA-V . . . . . . . . . . . . . . . . . . . . . . . . . 6 4.3 Benchmark Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 4.4... | https://arxiv.org/abs/2505.16933v1 |
while masked tokens [M] either stay masked with probability s/tor are replaced with meaningful content predicted by the model with probability 1−s/t. The training objective of masked diffusion models is the following upper bound on negative log- likelihood: Lθ=Z1 01 tEq(xt|x0) X {i|xi t=m}−logpθ(xi 0|xt) dt. (4) Fo... | https://arxiv.org/abs/2505.16933v1 |
Attention Mask In Fig. 4, we summarize the attention masks discussed in this work. Conventional autoregressive MLLMs utilize a standard causal mask, as shown in Fig. 4a, which restricts each token’s attention to itself and all previous tokens. LLaDA-V explores two additional alternatives: the Dialogue Causal Mask , whi... | https://arxiv.org/abs/2505.16933v1 |
surrounded by snow-capped mountains. There are two individuals visible in the image. - We see one person is taking a photograph on the left side of the image. - There is another person standing on the right side of the image. By counting these two individuals, we confirm that there are 2 people in the picture. Therefor... | https://arxiv.org/abs/2505.16933v1 |
arXiv:2505.16934v1 [cs.CL] 22 May 2025In-Context Watermarks for Large Language Models Yepeng Liu∗ University of FloridaXuandong Zhao UC Berkeley Christopher Kruegel UC Santa BarbaraDawn Song UC BerkeleyYuheng Bu University of Florida Abstract The growing use of large language models (LLMs) for sensitive applications ha... | https://arxiv.org/abs/2505.16934v1 |
the LLM exclusively through its API to obtain generated text. Once the watermarking instruction is set, users can interact with the LLM as usual—submitting queries and receiving responses—while the generated text automatically contains the embedded invisible watermark. One viable opportunity for conference organizers m... | https://arxiv.org/abs/2505.16934v1 |
the LLM. Post-hoc LLM Watermarking. Post-hoc watermarking methods embed watermarks into existing texts by transforming unwatermarked content into a watermarked version. These methods typically operate through controlled modifications of the original text, such as format transformations [ 36–39], lexical substitutions [... | https://arxiv.org/abs/2505.16934v1 |
detection process is agnostic to the LLM M. The watermark detector, D(·|k, τ) :Y∗7→R, operates using the knowledge of kandτto analyze the suspect text y. The detection of the watermark can be formulated as a hypothesis testing problem as follows: H0: The text is generated without the knowledge of kandτ. H1: The text is... | https://arxiv.org/abs/2505.16934v1 |
adversary (in this case, the reviewer) may also employ defensive strategies, such as detecting and removing the embedded instruction. In this paper, we primarily explore the potential application of ICW in the IPI setting. As such, a detailed investigation of attack and defense methods is left for future work. 3 Explor... | https://arxiv.org/abs/2505.16934v1 |
formats. Moreover, it is highly fragile to transformations like LLM paraphrasing, which may limit its application in broader scenarios. Note that this approach can be extended, like Cyrillic letter substitution or multi-bit encoding schemes [ 38]. 3.2.2 Initials ICW Watermark Generation. Initials ICW encourages the use... | https://arxiv.org/abs/2505.16934v1 |
word, select appropriate instances during generation, and increase the frequency of those words in the response, which may pose a significant challenge for current models. 3.2.4 Acrostics ICW Watermark Generation. For the sentence-level strategy, we explore the use of acrostics in ICW. The high-level idea is to embed a... | https://arxiv.org/abs/2505.16934v1 |
robust to editing and paraphrasing, as long as most of the sentence initial letter sequence is preserved. 4 Experiments 4.1 Experiment Settings Implementation Details. We evaluate our ICW methods in two different settings using two advanced proprietary LLMs, gpt-4o-mini [72] and gpt-o3-mini [73], where gpt-o3-mini poss... | https://arxiv.org/abs/2505.16934v1 |
Acrostics ICWs require substantially higher model capabilities. As shown in the table, these methods exhibit very low detection performance when used with GPT-4o-mini , suggesting that the corresponding watermarking instructions were largely ignored or not followed. However, their performance improves significantly wit... | https://arxiv.org/abs/2505.16934v1 |
compared to the baselines, likely because it relies on green words, mainly nouns, verbs, adjectives, and adverbs, which are targeted by the replacement procedure. Initials ICW consistently achieves high detection performance under both editing and paraphrasing attacks, outperforming the baselines. 4.2.3 Text Quality Th... | https://arxiv.org/abs/2505.16934v1 |
Future work can explore advanced prompt engineering, such as few-shot examples or chain-of-thought prompting, to better balance detectability, robustness, and text quality. Treating ICW as a new alignment task: As explored in Appendix C.3, current LLMs still struggle with Lexical ICW, particularly when handling large v... | https://arxiv.org/abs/2505.16934v1 |
Khazatsky, Christopher D Manning, and Chelsea Finn. Detectgpt: Zero-shot machine-generated text detection using probability curvature. In Interna- tional Conference on Machine Learning , pages 24950–24962. PMLR, 2023. [16] Edward Tian and Alexander Cui. Gptzero: Towards detection of ai-generated text using zero-shot an... | https://arxiv.org/abs/2505.16934v1 |
Watermarking text data on large language models for dataset copyright protection. arXiv preprint arXiv:2305.13257 , 2023. [31] Yepeng Liu, Xuandong Zhao, Dawn Song, and Yuheng Bu. Dataset protection via watermarked canaries in retrieval-augmented llms. arXiv preprint arXiv:2502.10673 , 2025. [32] Wenjie Qu, Dong Yin, Z... | https://arxiv.org/abs/2505.16934v1 |
Ruan, Huiyuan Wang, Qi Long, and Weijie J Su. Robust detection of watermarks for large language models under human edits. arXiv preprint arXiv:2411.13868 , 2024. [49] Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, and Weijie J Su. A statistical framework of watermarks for large language models: Pivot, detection efficiency... | https://arxiv.org/abs/2505.16934v1 |
Security Symposium (USENIX Security 24) , pages 1831–1847, 2024. [66] Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Zihao Wang, Xiaofeng Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, et al. Prompt injection attack against llm-integrated applications. arXiv preprint arXiv:2306.05499 , 2023. [67] Xiaogeng Liu, ... | https://arxiv.org/abs/2505.16934v1 |
Easy to follow and logically organized. 2. Accurate & Concrete: Provides precise facts, examples, or steps. Avoid vague or overly verbose expressions. 3. Contextually Relevant: Directly addresses the user’s intent and context. 4. “Green Word” Enriched (Most Important!): Try your best to seamlessly incorporate as many w... | https://arxiv.org/abs/2505.16934v1 |
done prior to injecting the watermarking instruction into the document. Next, the selected words and the watermarking instruction are inserted into the target document, instructing the inclusion of these words in subsequent responses. This two-step approach is necessary because the original green word list is too long ... | https://arxiv.org/abs/2505.16934v1 |
exclusively included in our watermarking instruction. •Acrostics ICW : To minimize unnaturalness in the watermarked text, we exclude low-frequency initial letters and retain only high-frequency ones to construct the letter list. Watermark key sequences are then generated by randomly sampling from this list. In our expe... | https://arxiv.org/abs/2505.16934v1 |
results indicate that Unicode ICW is highly fragile to various text transformations. The Letter, Lexical, and Acrostics ICWs exhibit a degree of robustness, maintaining high detectability even under paraphrasing. Language Models MethodsReplacement - 30% Deletion - 30% Paraphrase - ChatGPT ROC-AUC T@1%F T@10%F ROC-AUC T... | https://arxiv.org/abs/2505.16934v1 |
final output contains the same information as the original text and has roughly the same length. Do not leave out any important details when rewriting in your own voice. Output the result in the JSON format with nothing else: {"watermark":<0 or 1>, "paraphrase": <the paraphrased text> }. Table 7: Adaptive attack. Using... | https://arxiv.org/abs/2505.16934v1 |
struggle with tasks such as counting the number of occurrences of a specific letter in a word (e.g., the number of ‘r’s in ‘strawberry’), this strategy remains challenging even for advanced models. More strategy. Additionally, other sentence-level strategies could be explored in future work. For example, sentence struc... | https://arxiv.org/abs/2505.16934v1 |
significant biodiversity, offering shelter and resources for various species that thrive in more contained environments. Moreover, cultural and historical perceptions have influenced how these terms are used. Forests are often imbued with a sense of mystery, adventure, and grandeur, frequently featured in myths, legend... | https://arxiv.org/abs/2505.16934v1 |
affected by these events. Many Byzantine leaders and their subjects initially viewed the crusading project with cautious optimism. In theory, the arrival of crusaders was expected to provide additional military aid and financial support, which could help alleviate the mounting pressure from aggressive forces in the eas... | https://arxiv.org/abs/2505.16934v1 |
NovelSeek: Starting Point of Innovation NOVEL SEEK: When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification NovelSeek Team, Shanghai Artificial Intelligence Laboratory https://alpha-innovator.github.io/NovelSeek-project-page https://github.com/Alpha-Innovator/NovelSeek https://hug... | https://arxiv.org/abs/2505.16938v2 |
pro- posals, as well as achieving closed-loop feedback for the experimental validation of these proposals: •First, generating proposals that are both effective and novel is a complicated task. Autonomous systems must identify research gaps and generate hypotheses that are not only innovative but also scientifically val... | https://arxiv.org/abs/2505.16938v2 |
the contributions of this paper are summarized below: •Unified Multi-agent Framework for Diverse Scientific Research Tasks : We present NOVEL SEEK, a unified closed-loop scientific research framework that can automate the entire research cycle, including idea generation, idea-to-methodology transfor- mation, experiment... | https://arxiv.org/abs/2505.16938v2 |
depth of detail for exploring existing methodologies. This adaptability is crucial for effectively generating new ideas across different research contexts, and the primary responsibility of the Survey Agent is to search for scientific papers, offering two distinct modes to address the varying needs for depth and breadt... | https://arxiv.org/abs/2505.16938v2 |
large code-bases. Overall, the Code Review Agent offers de- tailed documentation that deepens the understanding of code repositories and supports innovation in scientific research. Idea Innovation Agent. The Idea Innovation Agent is an integral part of NOVEL SEEK, designed to enhance the creative and iterative processe... | https://arxiv.org/abs/2505.16938v2 |
idea, while credibility assesses its trustworthiness based on existing knowledge. Verifiability examines the idea’s testability through empirical methods. Novelty measures originality, and alignment ensures consistency with research goals. Moreover, for each dimension, the Assessment Agent provides a detailed evaluatio... | https://arxiv.org/abs/2505.16938v2 |
Agent coordinates all other agents within the sys- tem, facilitating collaboration by synchronizing tasks and managing data flow. This ensures the process remains efficient, coherent, and aligned with research objectives, allowing the framework to function as an effective research tool. Central to the Orchestration Age... | https://arxiv.org/abs/2505.16938v2 |
the literature corpus, and Mis the resulting methodological framework. Overall, through Methodology Initialization, the Method Development Agent effectively turns initial ideas into detailed, actionable methods, ready for further refinement. 2.2.2 Methodology Refinement After the initialization, the Methodology Develop... | https://arxiv.org/abs/2505.16938v2 |
implementation strategy, we designed an adaptive evolution approach for our implementation process. This approach involves structured iterations where each implementation attempt is followed by performance assessment and potential refinement. We maintain records of implementation decisions across iterations, which help... | https://arxiv.org/abs/2505.16938v2 |
comprises two years of hourly multivari- ate time series, including the target oil temperature and six power-load covariates, collected from transformer stations in two Chinese counties. We use DLinear (Zeng et al., 2023) as our baseline, an MLP-based forecasting model that decomposes each series into trend and seasona... | https://arxiv.org/abs/2505.16938v2 |
Vision-Language Model Fine-tuning (AutoVLM). We conduct experiments on filtered geometry subset of the URSA dataset (Luo et al., 2025), comprising manually curated multimodal QA pairs and CoT process. Natural images were excluded, and data were downsampled to control experimental budgets, enabling training completion w... | https://arxiv.org/abs/2505.16938v2 |
measured using the mean Intersection over Union (MIoU), which quantifies the average overlap between the predicted segmentation and the ground truth across all classes, providing a comprehensive assessment of the model’s segmentation accuracy. •AutoPCD. Following ONCE official evaluation metric, we merge the car, bus a... | https://arxiv.org/abs/2505.16938v2 |
0.155 0.00459 - 0.179 0.73 NOVEL SEEK 33.5 (+5.9) 0.152 0.00447 0.4346 0.170 0.77 Table 2: Performance comparison for six types of scientific research tasks. We conduct experiments using 10 NOVESEEK generated ideas for each task, where baseline codes for Auto2DSeg, AutoPCDet, and AutoVLM are project-level, consisting o... | https://arxiv.org/abs/2505.16938v2 |
This im- provement is mainly attributed to the idea-to-methodology feature of NOVEL SEEK, which enables the concretization of high-level ideas. Additionally, through the process of multi-round experimental planning and execution, the submodules of the AI-generated methodology are progressively integrated into the basel... | https://arxiv.org/abs/2505.16938v2 |
train-set=60) 35.4 35.2 34.5 35.2 33.7 34.8±1.1 Baseline (train-set=100) 38.8 30.6 34.8 39.0 34.5 35.5 ±4.9 GAT (ours, train-set=100) 36.9 39.1 34.4 41.4 35.0 37.4 ±4.0 ADAGT (ours, train-set=100) 38.5 38.0 38.6 37.9 40.4 38.7±1.7 debug stage. As shown in Tab. 5 and Tab. 6. As mentioned in Sec. 3.1.3, we select top 5 i... | https://arxiv.org/abs/2505.16938v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.