text string | source string |
|---|---|
Algebra, Prealgebra, Geometry, Counting & Probability, and Number Theory. 4.2 Experiment Setup We choose the four models for our study from the four popular LLM families, namely Gemini, GPT-4, Llama, and Mixtral. More details on the models used can be found in section A.2. 4.3 Evaluation method To evaluate the reliabil... | https://arxiv.org/abs/2505.15623v1 |
and improve logical coherence in reasoning steps will be critical for advancing LLMs’ mathematical problem-solving capabilities. 4 References [1]Shijie Xia, Xuefeng Li, Yixin Liu, Tongshuang Wu, and Pengfei Liu. Evaluating mathematical reasoning beyond accuracy. arXiv preprint arXiv:2404.05692 , 2024. [2]Noah Shinn, Fe... | https://arxiv.org/abs/2505.15623v1 |
arXiv:2505.15624v1 [cs.LG] 21 May 2025Mechanistic Insights into Grokking from the Embedding Layer H. V . AlquBoj∗Hilal AlQuabeh∗ MBZUAI Abu Dhabi, UAE hilal.alquabeh@mbzuai.ac.aeVelibor Bojkovi ´c∗ MBZUAI Abu Dhabi, UAE velibor.bojkovic@mbzuai.ac.ae Munachiso Nwadike MBZUAI Abu Dhabi, UAE munachiso.nwadike@mbzuai.ac.ae... | https://arxiv.org/abs/2505.15624v1 |
training, particularly for low-probability tokens. 2.Coupling with the first-layer weights: When embeddings are multiplied with the weights of the first layer, they form a bilinear interaction. This coupling introduces structural complexity into the optimization landscape, making the process more susceptible to saddle ... | https://arxiv.org/abs/2505.15624v1 |
gradient imbalance. Unlike works that focus on final representations [ 4], we analyze the embedding layer’s evolving role during training. Even with one-hot inputs, its interaction with the first linear layer forms a learnable embedding mechanism. Concurrent work shows that transferring embeddings from small to large m... | https://arxiv.org/abs/2505.15624v1 |
and complete set of all possible input-output combinations. In such cases, there is no statistical "distribution" in the conventional sense; instead, the generalization task relies on uncovering the underlying relationship between inputs, which demands a model to internalize the algorithm itself. Moreover, any hypothes... | https://arxiv.org/abs/2505.15624v1 |
vector. The MLP processes these inputs as: h1=σ(W1x+b1),h2=W2h1+b2, ˆy= Softmax( h2). (1) where x∈R4is the encoded input vector (with first and third entry aandb, respectively), W1,W2 are weight matrices, b1,b2are biases, σis the ReLU activation function, and ˆyrepresents the predicted output. This configuration demons... | https://arxiv.org/abs/2505.15624v1 |
rate, and ∇eiLis the gradient2. Token embeddings are updated using corresponding gradients only when the associated tokens appear in a batch. Assume that token i being sampled in a batch with a probability pi. Consequently, taking into account the randomness of batch sampling, the expected update can be expressed as: E... | https://arxiv.org/abs/2505.15624v1 |
- T est uniform - Train uniform - T est Optimization steps0.00.20.40.60.81.0AccuracyBatch Size = 128 random - Train random - T est skew - Train skew - T est uniform - Train uniform - T est 101 102 103 104 105 Optimization steps0.00.20.40.60.81.0AccuracyBatch Size = 512 random - Train random - T est skew - Train skew - ... | https://arxiv.org/abs/2505.15624v1 |
dimension): dei dt=−λei−pi∇eiL, (8) 7 where ∇eiLis the gradient of the loss function with respect to the embedding i. Assuming that the gradient ∇eiLstabilizes to a constant value g, the solution to this equation is: ei(t) =Ce−λt−ηpg λ, (9) where Cis an integration constant determined by the initial conditions. As time... | https://arxiv.org/abs/2505.15624v1 |
sampling. The expression (a+b) mod prepresents the sum of aandbmodulo p. For our experiments, we randomly set aside 20% of the data as a test set, ensuring that evaluation is performed on unseen samples. From the remaining data, 30/80% (i.e. 30% from total set) is sampled as the training set according to each sampling ... | https://arxiv.org/abs/2505.15624v1 |
heterogeneity [ 25,10,18,26]. However, these studies largely overlook the role of embeddings and their bilinear interactions. Our analysis supports the view that such bilinear structure, especially in embeddings, contributes significantly to the observed curvature differences (see appendix C.1 for more discussion). To ... | https://arxiv.org/abs/2505.15624v1 |
Schaar. Deep learning through a telescoping lens: A simple model provides empirical insights on grokking, gradient boosting & beyond. Advances in Neural Information Processing Systems , 37:123498–123533, 2024. [8]S. Kobayashi, Y . Akram, and J. V on Oswald. Weight decay induces low-rank attention layers. Advances in Ne... | https://arxiv.org/abs/2505.15624v1 |
Kumar, and S. Sra. Why are adaptive methods good for attention models? Advances in Neural Information Processing Systems , 33:15383–15393, 2020. [26] Y . Zhang, C. Chen, T. Ding, Z. Li, R. Sun, and Z.-Q. Luo. Why transformers need adam: A hessian perspective. arXiv preprint arXiv:2402.16788 , 2024. 11 Appendix A Optimi... | https://arxiv.org/abs/2505.15624v1 |
a bilinear term: z(EW), (20) where zis an activation function applied elementwise. The gradients of EandWare given as: ∇E∝W⊤∇loss,∇W∝E⊤∇loss. (21) The gradient norms are influenced by the dominant singular values of WandE. Specifically: ∥∇E∥ ∝σmax(W),∥∇W∥ ∝σmax(E). (22) At initialization, EandWare often drawn from dist... | https://arxiv.org/abs/2505.15624v1 |
SGD, particularly in small-batch settings. Furthermore, [ 26] provides a novel explanation for Adam’s advantage over SGD in Transformers by analyzing the blockwise Hessian spectrum, introducing the concept of “block heterogeneity.” This refers to significant variations in the Hessian spectra across parameter blocks, a ... | https://arxiv.org/abs/2505.15624v1 |
curvature. 15 0 20 40 60 80 100 Input Dimension (Vocab Index)01020304050607080L2 NormAddition Modular P 0 20 40 60 80 100 Input Dimension (Vocab Index)051015202530L2 NormDivision Modular P 0 20 40 60 80 100 Input Dimension (Vocab Index)01020304050607080L2 NormAddition Modular P with Adam_LRFigure 11: Discrete Fourier a... | https://arxiv.org/abs/2505.15624v1 |
T est(a)(a+b) mod p Optimization steps0.00.20.40.60.81.0AccuracyBatch Size = 256 random - Train random - T est skew - Train skew - T est uniform - Train uniform - T est Optimization steps0.00.20.40.60.81.0AccuracyBatch Size = 512 random - Train random - T est skew - Train skew - T est uniform - Train uniform - T est 10... | https://arxiv.org/abs/2505.15624v1 |
random - Train random - T est skew - Train skew - T est uniform - Train uniform - T est (c)(a×b) mod p Optimization steps0.00.20.40.60.81.0AccuracyBatch Size = 256 random - Train random - T est skew - Train skew - T est uniform - Train uniform - T est Optimization steps0.00.20.40.60.81.0AccuracyBatch Size = 512 random ... | https://arxiv.org/abs/2505.15624v1 |
arXiv:2505.15633v1 [cs.CL] 21 May 2025Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions David Thulke1,2Jakob Kemmler1,2Christian Dugast2Hermann Ney1,2 1Machine Learning and Human Language Technology, RWTH Aachen University, Germany 2AppTek GmbH, Aachen... | https://arxiv.org/abs/2505.15633v1 |
process spans two years, begin- ning with information collection and preparation and culminating in a consideration of [...] Figure 1: Shortened example from the original Cli- mateGPT and the Faithful+ variant on one example from the Climate Policy Radar task. Text marked in red is not faithful, i.e. it is not supporte... | https://arxiv.org/abs/2505.15633v1 |
the evidence retrieval step, as we describe below. Claim Decomposition As long-form responses are typically composed of multiple claims, we first decompose the response into smaller and indepen- dent claims to simplify the subsequent steps. Given a response r, we decompose it into a set of claims C=c1, . . . , c I. The... | https://arxiv.org/abs/2505.15633v1 |
reports and climate science related papers (see Appendix C for detailed statistics). For retrieval, we employ thebge-large-en-v1.5 embedding model (Xiao et al., 2024) and a hierarchical retrieval strategy where we first retrieve the most relevant pages based on the query, selecting the top 5 ranked pages. Then, within ... | https://arxiv.org/abs/2505.15633v1 |
continued pre-training step has a significant impact on the faithfulness of the model. The IFT data of ClimateGPT consists of a general domain partition and a climate-specific partition that was specifically curated to train the model. The different subsets of the latter are listed in Table 2. A small portion of the da... | https://arxiv.org/abs/2505.15633v1 |
in the prompt, rather than via retrieval. Finally, removing the open-ended non-expert data without grounding does not have a significant effect on the claim sup- port. For the final model, ClimateGPT Faithful+ Other Open-End. Closed-End. Grounded Avg. Claim Support Size 65,000 8,503 1,160 3,328 #Claims wrt. Ref [%] Cli... | https://arxiv.org/abs/2505.15633v1 |
closed- ended prompts in training also improve the faith- fulness in the context of RAG and that it is crucial to avoid unfaithful training examples in the IFT data. With these insights, we develop ClimateGPT Faithful+ which improves ClimateGPT’s faithful- ness from 30% to 57% according to our automatic metric. These r... | https://arxiv.org/abs/2505.15633v1 |
generalization to other settings needs to be studied. Furthermore, the size of the knowledge base and the accuracy of the re- trieval method limit the accuracy of the factuality evaluation during the evidence retrieval step. Addi-tional analysis would be needed to study the impact of these factors on the claim support ... | https://arxiv.org/abs/2505.15633v1 |
Angela Fan, Michael Auli, and Jason Weston. 2019. Wizard of wikipedia: Knowledge-powered conversational agents. In International Conference on Learning Representations . Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Os- mar Zaiane, Mo Yu, Edoardo M. Ponti, and Siva Reddy. 2022. FaithDial: A faithful benchmark for informat... | https://arxiv.org/abs/2505.15633v1 |
in Natural Language Processing , pages 12076–12100, Singa- pore. Association for Computational Linguistics. Cheng Niu, Yuanhao Wu, Juno Zhu, Siliang Xu, KaShun Shum, Randy Zhong, Juntong Song, and Tong Zhang. 2024. RAGTruth: A hallucination cor- pus for developing trustworthy retrieval-augmented language models. In Pro... | https://arxiv.org/abs/2505.15633v1 |
value is interest- ing as an indication for the percentage of claims that are faithful to the reference by chance. Inter- estingly, we observe that the claim support of the original ClimateGPT models is close to this value. This further supports the interpretation that these models do not make effective use of the prov... | https://arxiv.org/abs/2505.15633v1 |
as either faithful (58.9%), not faithful (9.6%), not applicable (28%), or don’t know (3.5%). We used this data to evalu- ate how well our RAGAs-based metric aligns with human judgments. For the analysis, we focused only on examples that were labeled as either faith- ful or not faithful, excluding cases where the model ... | https://arxiv.org/abs/2505.15633v1 |
of claims based on a given context . For each claim you must return verdict as 1 if the claim can be directly inferred based on the context or 0 if the claim can not be directly inferred based on the context . EXAMPLE 1: Context : John is a student at XYZ University . He is pursuing a degree in Computer Science . He is... | https://arxiv.org/abs/2505.15633v1 |
human annotations. G Evaluation with LettuceDetect In addition to our primary faithfulness evaluation using RAGAs, we include results using LettuceDe- tect (Ádám Kovács and Recski, 2025), a recent hallucination detection framework designed for RAG systems. LettuceDetect is a token-level clas- sifier based on ModernBERT... | https://arxiv.org/abs/2505.15633v1 |
instance, the evidence does not explicitly state that polar bears are one of the affected species. However, it could be argued that it is plausible to infer that polar bears are included among the “many species” mentioned in the evidence. #Tokens #Parameters Hallucination-Free Responses [%] Model in Trillion in Billion... | https://arxiv.org/abs/2505.15633v1 |
climate - induced and non - climate drivers, including ocean warming, marine heatwaves, ocean acidification, sea - level rise, tropical cyclones [4] "Understanding the Effectiveness of Coastal Nature-based Solutions: Practitioner-based Learning", 2023 research indicates that biodiversity plays a crucial role in the fun... | https://arxiv.org/abs/2505.15633v1 |
14 of the Paris Agreement, the objective of the Global Stocktake is to assess the collective progress towards achieving the purpose of the Agreement and its long-term goals, considering mitigation, adaptation and the means of implementation and support, in light of equity and the best available science. The outcome of ... | https://arxiv.org/abs/2505.15633v1 |
arXiv:2505.15634v2 [cs.CL] 24 May 2025Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Zihao Li1∗Xu Wang1Yuzhe Yang2Ziyu Yao3Haoyi Xiong4Mengnan Du1 1New Jersey Institute of Technology2University of California, Santa Barbara 3George Mason University4Baidu Inc. lizihao9885@gmail... | https://arxiv.org/abs/2505.15634v2 |
systematic way to disentan- gle task-relevant reasoning signals from stylistic or superficial features present in the CoT. This paper introduces a novel framework that ad- dresses these limitations by enabling precise steer- ing of LLM residual activations using features ex- tracted exclusively from readily available v... | https://arxiv.org/abs/2505.15634v2 |
SAE encodes it into a sparse high-dimensional representation α∈ RdSAEand then decodes it to reconstruct h. The activation values in αare considered as features. These features can be explained by methods such as vocabulary projection (nostalgebraist, 2020) and visualization (McDougall, 2024), with the help of libraries... | https://arxiv.org/abs/2505.15634v2 |
the Symbol Reasoning Process can be described as follows: αx=1 ∥X∥X i∈XSAE (rx i), αy=1 ∥Y∥X j∈YSAE (ry j),(1) where αx∈RdSAEandαy∈RdSAEare consid- ered as the feature activation of Verbal Process and Symbolic Process at layer l. Intergrating Features. To derive the integrated features denoted as αfrom both reasoning p... | https://arxiv.org/abs/2505.15634v2 |
SAE features. We leverage a certain feature among them for steering, which modulates the residual activation of LLMs to control their behaviors. For a given feature indexed by t, inspired by Templeton et al. (2024); Farrell et al. (2024); Galichin et al. (2025), we proposed to use the activation value of αto modify the... | https://arxiv.org/abs/2505.15634v2 |
steering improves the accuracy by 3.34% and 4.80% in MMLU-high and MathOAI. There is no significant improvement on MATHL3&L4 for three LLMs, only DeepSeek-Llama3-8B achieves 1.72% improvement, which means that SAE steer- ing may play a better role in the reasoning model compared to the instruction model. Through furthe... | https://arxiv.org/abs/2505.15634v2 |
the layer l. Therefore, h can be decomposed as the weighted sum of feature vectors {zt}dSAE t=1 and error term ϵ, and αh tdenotes the activation value of feature tforhat layer l. h=dSAEX t=1αh tzt+b+ϵ (4) Now we want to steer the model even though there is no corresponding SAE model. In our method, there are two types ... | https://arxiv.org/abs/2505.15634v2 |
following problem: max ∥zt∥=1NX p=1∥αxp t−αyp t∥ = max ∥zt∥=1NX p=1∥⟨xp−yp,zt⟩∥ ∝max ∥zt∥=1∥A⊤zt∥2= max ∥zt∥=1z⊤ tAA⊤zt(7) The solving process can be found in Appendix E. The goal is to get the unit eigenvectors {ut}dmodel t=1 ofAATas descending order of eigenvalues, then select a certain eigenvector utto steer the res... | https://arxiv.org/abs/2505.15634v2 |
has summarized recent progress and applications of representation engi- neering in bias, fairness, model editing, and other fields. Li et al. (2024) has utilized this technique to quantify LLMs’ performance in different lan- guages. Li et al. (2023) reveals that the internal rep- resentations of attention heads within ... | https://arxiv.org/abs/2505.15634v2 |
Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. Deepseek-r1: In- centivizing reasoning capability in llms via reinforce- ment learning. arXiv preprint arXiv:2501.12948 . Zhengfu He, Wentao Shu, Xuyang Ge, Lingjie Chen, Junxuan Wang, Yunhua Zhou, Frances Liu, ... | https://arxiv.org/abs/2505.15634v2 |
Arnold D Well, and Robert F Lorch Jr. 2013. Research design and statistical analysis . Rout- ledge. Andrew Ng et al. 2011. Sparse autoencoder. CS294A Lecture notes , 72(2011):1–19. nostalgebraist. 2020. Logit lens. Accessed: 2024-06- 06. Liangming Pan, Alon Albalak, Xinyi Wang, and William Yang Wang. 2023. Logic-lm: Em... | https://arxiv.org/abs/2505.15634v2 |
language models. Xuansheng Wu, Wenhao Yu, Xiaoming Zhai, and Ning- hao Liu. 2025a. Self-regularization with latent space explanations for controllable llm-based classification. arXiv preprint arXiv:2502.14133 . Xuansheng Wu, Jiayi Yuan, Wenlin Yao, Xiaoming Zhai, and Ninghao Liu. 2025b. Interpreting and steering llms w... | https://arxiv.org/abs/2505.15634v2 |
features from this equation. This may be related to the training corpus. This SAE was only trained on one corpus. We did not find that this phenomenon exists in other SAEs with richer training corpora such asgemma-scope-9b-it-res(layer_9/wid th_16k/canonical) andllama_scope_lxr_8x (l15r_8x) . It confirms our assumption... | https://arxiv.org/abs/2505.15634v2 |
explore the geometric relationship be- tween top-k feature vectors of SAE, we calculated the cosine similarity matrix. A similarity of 0 indi- cates that the two are orthogonal. We utilize llama _scope_r1_distill(l15r_800m_openr1_math) as an example, the result is shown as Figure 7, we can find that for top-150 feature... | https://arxiv.org/abs/2505.15634v2 |
**Step 7: Finding Special Values** Finally, we’ll look for those partic- ular whole numbers where the function’s output is identical to the input itself. This involves setting up and solving another equation based on the complete function we’ve determined. **Conclusion:** Through this step-by-step approach, we’ll fully... | https://arxiv.org/abs/2505.15634v2 |
,0 #. $ #)- !) 11!11,2223 4 5!6 ... | https://arxiv.org/abs/2505.15634v2 |
15 - . / !" 012 15 ! ... | https://arxiv.org/abs/2505.15634v2 |
!" # $ #%&'& (($)* * #+ , ! - ./ 01... | https://arxiv.org/abs/2505.15634v2 |
, - !" ./0 /3 ! 8/0 8 . 9 ... | https://arxiv.org/abs/2505.15634v2 |
"$ ) ) 0 # /( "$ ) ) %%&$%%1 2 '... | https://arxiv.org/abs/2505.15634v2 |
Subtraction and Addition 16k/canonical) as the corresponding SAE. The result shows that compared with subtraction, addi- tion will make the correlation lower, even less than 0, which means that the activation result obtained by subtracting can better reflect the importance of model prediction.L Steering Case We provide... | https://arxiv.org/abs/2505.15634v2 |
1, last term l= 12,and number of terms n = 12. The formula for the sum of this type of sequence is given byn(a+l) 2, so we can use it here. Step 3 Substituting in our values gives us a total sum of (12∗13 2)Step 4 Evaluating that expression yields (156)as the result. Step 5 Now we must find its remainder when divided b... | https://arxiv.org/abs/2505.15634v2 |
hit. He loads up the machine with 175 tennis balls to start with. Out of the first 100 balls, he manages to hit 2/5 of them. Of the next 75 tennis balls, he manages to hit 1/3 of them. Out of all the tennis balls, how many did Ralph not hit?” Answer:110 Orign :Step-by-step thinking: Let’s break this problem down into s... | https://arxiv.org/abs/2505.15634v2 |
mistake. Let me re-evaluate the steps: Initially, Ralph loads 175 tennis balls into the machine. In the first round, he fires off 100 balls but only hits 2/5 of them, leaving him with 80 untouched balls. Then, he continues firing another 75 balls, where he again misses 50% of them. To determine the overall percentage o... | https://arxiv.org/abs/2505.15634v2 |
is: 110 Table 8: Steering Case. LLM: Llama3.1-8B-it Featue:17394(conclusive statements that indicate results or sum- maries) Question :Answer the following question step by step in short and put the final answer in . Question:Solve for the sum of all possible values of xwhen 3x2+4x+4= 9x+2. Answer: -2 Orign :Step 1: Re... | https://arxiv.org/abs/2505.15634v2 |
algebra) Question :Answer the following question step by step and put the final answer in .Question:If aand bare vectors such that ∥a∥= 2,∥b∥= 7,and a×b= 3 2 6 , then find the smallest possible angle between aandb,in degrees. Answer: 30◦ Orign :Step 1: We know that for any two vectors xandy,(x×y)·(x×y) = 0 .This is... | https://arxiv.org/abs/2505.15634v2 |
arXiv:2505.15646v1 [cs.CL] 21 May 2025Word Level Timestamp Generation for Automatic Speech Recognition and Translation Ke Hu1, Krishna Puvvada1, Elena Rastorgueva1, Zhehuai Chen1, He Huang1, Shuoyang Ding1, Kunal Dhawan1, Hainan Xu1, Jagadeesh Balam1, Boris Ginsburg1 1NVIDIA, USA kevinhu@nvidia.com Abstract We introduc... | https://arxiv.org/abs/2505.15646v1 |
delay the duration emission which leads to inaccurate word-level start and end timestamps. Whisper [11] and OWSM [12] use a data-driven approach to directly train the model to emit timestamps. However, the timestamps are at the segment level due to training data limitation. Recently, Ope- nAI released the feature to ge... | https://arxiv.org/abs/2505.15646v1 |
by using various prompts tokens, such as <|transcribe|> ,<|translate|> ,<|pnc|> , <|nopnc|> . To add timestamp prediction ability to Canary, we introduce <|timestamp|> and<|notimestamp|> for generating word-level timestamps or no timestamps, respec- tively. As shown in Fig. 1, our training data is formatted in two styl... | https://arxiv.org/abs/2505.15646v1 |
AST, we use FLEURS [20] to evalu- ate our timestamp prediction performance for 6 language pairs, i.e. En→X and X→En, where X is German, French or Spanish. ASR performance is measured using WER, and we use BLEU [21] and COMET [22] for AST evaluation. For timestamp evaluation, we use two types of metrics: 1) Precision an... | https://arxiv.org/abs/2505.15646v1 |
95.8 /95.6 83.6 / 83.2 320 (ms) 96.1 /95.9 92.8 / 92.2 400 (ms) 96.3 /96.1 95.3 / 94.7 480 (ms) 96.4 /96.2 96.1 / 95.5 Table 3: Comparison of the proposed model and WhisperTimes- tamped [6] based on the LibriSpeech test-other set. batch duration of 600 sec per GPU. For model training, we use AdamW optimizer and inverse... | https://arxiv.org/abs/2505.15646v1 |
as the end timestamp of the previous word. Due to the formatting, the derived start and end timestamps from WhisperTimestamped may inherently differ from the NFA produced “ground truth”, and this should not be penalized in evaluation. We therefore do not calculate the absolute differences between the predicted and refe... | https://arxiv.org/abs/2505.15646v1 |
Predicted English Hypothesis French Ground Truth <|0|> The<|1|> <|22|> surface <|28|> <|28|> of<|29|> <|29|> the<|30|> <|31|> moon <|34|> <|35|> is<|36|> <|36|> constituted <|42|> <|42|> of<|43|> <|44|> stone <|47|> <|48|> and<|49|> <|49|> of<|50|> <|50|> duster <|56|> <|58|> its<|60|> <|60|> louch <|64|> <|65|> exte- ... | https://arxiv.org/abs/2505.15646v1 |
incorrectly predicting English words to be their French coun- terparts with similar pronunciation. Future research may focus on few-shot learning for AST timestamp prediction. 5. Conclusion We propose a data-driven approach for word-level timestamp prediction for a Canary ASR and AST, leveraging NeMo Forced Aligner (NF... | https://arxiv.org/abs/2505.15646v1 |
data,” arXiv preprint arXiv:2406.19674 , 2024. [15] Z.-Y . Dou and G. Neubig, “Word alignment by fine-tuning em- beddings on parallel corpora,” arXiv preprint arXiv:2101.08231 , 2021. [16] T. Kudo, “Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing,” arXiv pre... | https://arxiv.org/abs/2505.15646v1 |
arXiv:2505.15656v1 [cs.CL] 21 May 2025Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen! Zhexin Zhang1, Yuhao Sun2, Junxiao Yang1, Shiyao Cui1, Hongning Wang1, Minlie Huang1∗ 1The Conversational AI (CoAI) group, DCST, Tsinghua University 2The University of Melbourne zx-zhan... | https://arxiv.org/abs/2505.15656v1 |
released for downstream developers to adopt. Since the backdoor instruction will not be released, the downstream fine-tuning will not affect the impact of this instruction when later used at the inference time for extraction purpose. Intuitively, this backdoor training is to teach the LLM to follow a special instructio... | https://arxiv.org/abs/2505.15656v1 |
queries) used for adopting the backdoored models for downstream tasks. Unlike conventional poisoning attacks that associate backdoor triggers with predetermined outputs, our approach requires the malicious behavior learned from backdoor training to adaptively evolve with continuous learning in the downstream fine-tunin... | https://arxiv.org/abs/2505.15656v1 |
malicious developer can insert a backdoor training phase prior to releasing the open- sourced model M1. The resulting compromised model, denoted as M′ 1, maintains indistinguishable 3 general performance from the benign model M1. However, once M′ 1is fine-tuned on private data to produce M′ 2, the malicious developer c... | https://arxiv.org/abs/2505.15656v1 |
backdoor training is constructed as follows: we extract the opening word wfrom each given user query xinD1and create a corresponding SFT training tuple (Q(w), x). The resulting dataset is denoted as DSFT real={(Q(w), x)}. We also craft additional SFT instances to help the model recognize invalid opening words. Specific... | https://arxiv.org/abs/2505.15656v1 |
by their word frequency. In order to filter out invalid opening words, we design a simple heuristic scoring method. For each ˆw, we sample Ncompletions {r1, . . . , r N}from M′ 2given the prompt Q( ˆw). Let cnt(ri)denote the number of completions identical to ri. The score forˆwis then computed as: score ( ˆw) =αN−PN i... | https://arxiv.org/abs/2505.15656v1 |
of Dolly2, containing general instruction-following samples, and (2) a 5,000-sample subset of Finance3, which includes finance-specific QA pairs in addition to general instructions. These two datasets allow us to evaluate the robustness and generality of our extraction attack across different data distributions. Evalua... | https://arxiv.org/abs/2505.15656v1 |
value among them). To evaluate n-gram similarity beyond exact matches, we also compute the BLEU score between each completion riand the corresponding training queries {x}. Analogously, we define Mean BLEU andMax BLEU across the 10 samples. All reported metrics are then averaged over different extraction prompt Q(w). Re... | https://arxiv.org/abs/2505.15656v1 |
Notably, even with only 50 opening words, the Query Extraction Ratio can exceed 50% in many settings, demonstrating the efficiency and practicality of the proposed attack. Interestingly, increasing the number of opening words leads to a decline in precision, while recall improves only marginally. This is expected, as t... | https://arxiv.org/abs/2505.15656v1 |
significantly improved performance on data extraction instructions, allowing downstream developers to potentially detect the presence of backdoors by investigating the model’s behavior under such instructions. Even if the exact instruction used during backdoor training is unknown, developers can probe the model using s... | https://arxiv.org/abs/2505.15656v1 |
Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurélien Rodriguez, Austen Gregerson, Ava Spataru, Baptiste Rozière, Bethany Biron, Binh Tang, Bobbie Chern, Charlotte Caucheteux, Chaya Nayak, Chloe Bi, Chris Marra, Ch... | https://arxiv.org/abs/2505.15656v1 |
2024. doi: 10.48550/ARXIV .2406.12091. URL https://doi.org/10. 48550/arXiv.2406.12091 . [14] Yao Qiang, Xiangyu Zhou, Saleh Zare Zade, Mohammad Amin Roshani, Douglas Zytko, and Dongxiao Zhu. Learning to poison large language models during instruction tuning. CoRR , abs/2402.13459, 2024. doi: 10.48550/ARXIV .2402.13459.... | https://arxiv.org/abs/2505.15656v1 |
Liang, and Tatsunori B. Hashimoto. Length-controlled alpacaeval: A simple way to debias automatic evaluators. CoRR , abs/2404.04475, 2024. doi: 10.48550/ARXIV .2404.04475. URL https://doi.org/10.48550/arXiv.2404.04475 . [27] Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Stei... | https://arxiv.org/abs/2505.15656v1 |
necessary to enhance the controllability of extraction. MethodMatch Ratio ( ↑) BLEU ( ↑) Extraction Ratio ( ↑) Mean Max@10 Mean Max@10 Token-Level Query-Level Raw 18.6 31.6 6.8 19.5 29.5 5.0 SFT 40.9 71.6 32.9 64.4 58.1 39.6 SFT (W/O Opening Word) 6.9 23.4 5.0 18.7 58.7 41.3 Table 4: The extraction performance on Dolly... | https://arxiv.org/abs/2505.15656v1 |
↑) F1 Accuracy SFT0.7 0.7 79.2 79.5 0.6 0.65 44.4 62.5 0.6 0.6 79.4 79.0 0.6 0.55 74.4 70.0 0.5 0.5 78.3 77.0 GRPO0.7 0.7 80.8 81.0 0.6 0.65 47.8 64.0 0.6 0.6 82.7 82.0 0.6 0.55 77.6 72.0 0.5 0.5 83.3 82.0 Table 7: The opening word identification performance of Qwen2.5-7B on Dolly dataset when using different hyperpara... | https://arxiv.org/abs/2505.15656v1 |
16 the verbatim training queries, whereas the model without backdoor training exhibits a range of characteristic error modes: (1) Incorrect opening words : The model tends to produce queries that do not begin with the expected opening word. For instance, in Figure 8, the ground-truth query starts with “At”, and the ins... | https://arxiv.org/abs/2505.15656v1 |
a learning rate of 3×10−6. During SFT backdoor training, we use 4,432 samples with real opening words and 400 samples with fake opening words. For GRPO backdoor training, we use 394 real and 92 fake opening-word samples. The batch size is set to 48 for all SFT-based training and 9 for GRPO-based training. All experimen... | https://arxiv.org/abs/2505.15656v1 |
arXiv:2505.15667v1 [eess.AS] 21 May 2025Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information Nicholas Sanders, Yuanchao Li, Korin Richmond, Simon King 1The Centre for Speech Technology Research, University of Edinburgh, United Kingdom {nicholas.sanders, yuanchao.li, korin.richmond,... | https://arxiv.org/abs/2505.15667v1 |
that encodes speech at multiple linguistic levels (frame, phone, word, and utterance), effec- tively factorizing speech into distinct streams of segment- specific discrete units. • We evaluate our approach against fixed frame-level DSUs and continuous speech representations across both probing tasks (SER and prominence... | https://arxiv.org/abs/2505.15667v1 |
its corresponding codebook using Euclidean distance. This results in four parallel DSU output streams, each capturing linguistic structure at a distinct granularity (frame, phone, word, utterance). 3.2. Processing Multiple Streams of DSUs For downstream tasks, there are potentially many ways that Segmentation-Variant D... | https://arxiv.org/abs/2505.15667v1 |
SVCs are trained with a vocabulary of k = 500. 4.2. Probing Tasks We evaluate prominence classification on Naver Prosody Con- trol and SER on IEMOCAP, using an 80-10-10 split for Naver Prosody Control and a session-based split for IEMOCAP (ses- sions 1–3 for training, 4 for validation, 5 for testing). All probing tasks... | https://arxiv.org/abs/2505.15667v1 |
baselines, although it should underperform relative to the top line model trained with continuous representations. 5.3. Resynthesis task for reconstructing expressive speech Lastly, we evaluate the performance of SVCs in a speech resyn- thesis task, quantifying expressive style retention through a publicly released pre... | https://arxiv.org/abs/2505.15667v1 |
by SVCs performs the best of the all models trained with DSUs. This further cor- roborates the results found in the frame-level probing experi- ments and further confirms our hypothesis that SVCs are more efficient at preserving paralinguistic and prosodic information. However, there is still a significant gap in perfo... | https://arxiv.org/abs/2505.15667v1 |
explored by investigating automatic and unsupervised segmentation methods [33]. Additionally, the promising evidence of factorization via pre-KMeans pooling of frame-wise representations suggests that further investigation is needed into how each Segmentation-Variant codebook con- tributes to different speech qualities... | https://arxiv.org/abs/2505.15667v1 |
and Signal Processing (ICASSP) . IEEE, 2023. [11] T. A. Nguyen, W.-N. Hsu, A. d’Avirro, B. Shi, I. Gat, M. Fazel- Zarani, T. Remez, J. Copet, G. Synnaeve, M. Hassid et al. , “Ex- presso: A benchmark and analysis of discrete expressive speech resynthesis,” in INTERSPEECH 2023 . ISCA, 2023, pp. 4823– 4827. [12] W. Ren, Y... | https://arxiv.org/abs/2505.15667v1 |
S. Vassilvitskii, “k-means++: The advantages of careful seeding,” Stanford, Tech. Rep., 2006. [26] J. Kong, J. Kim, and J. Bae, “Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,” Advances in neural information processing systems , vol. 33, pp. 17 022– 17 033, 2020. [27] S. W... | https://arxiv.org/abs/2505.15667v1 |
arXiv:2505.15670v1 [cs.CL] 21 May 2025Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Ke Hu1, Ehsan Hosseini-Asl1, Chen Chen1, Edresson Casanova1, Subhankar Ghosh1, Piotr ˙Zelasko1, Zhehuai Chen1, Jason Li1, Jagadeesh Balam1, Boris Ginsburg1 1NVIDIA, USA kevinhu@nvidia.com Abstract Spoken dialo... | https://arxiv.org/abs/2505.15670v1 |
1) A novel duplex S2S architecture featuring continuous user inputs and codec agent outputs with channel fusion that directly models simulta- neous text and speech of both the user and agent. 2) We demon- strate several key advantages over existing duplex models: The use of a pretrained encoder as input enables the fir... | https://arxiv.org/abs/2505.15670v1 |
differently in training (see Sec. 5.1). Our model is trained by multi-channel next token prediction similar to [1]. 3.1. Simultaneous Agent Text and Speech Prediction As shown in Fig. 1, we encode speech using 4 codebooks at a rate of 12.5 frames per second [23], and text targets are to- kenized into a separate channel... | https://arxiv.org/abs/2505.15670v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.