text string | source string |
|---|---|
Setting: Setting of Conversation. Table 16: Complete disclosure rate analysis: direct and inference privacy leakage (%), lower is better. ModelDirect privacy leakage Inference leakage Bank Account Driver License Phone Number Pwd SSN Address Age Ethnicity Setting no aug aug no aug aug no aug aug no aug aug no aug aug no... | https://arxiv.org/abs/2505.16211v1 |
performance relative to baseline; ↓indicates worse performance. Subscripts show the difference from the baseline. Table 18: Model inference accuracy (%), higher is better. Model Age Ethnicity Setting Open-source Models Qwen2-Audio 22.0 ↓1.5 16.0 ↓13.7 59.0 ↓26.2 SALMONN – 16.2 ↓13.5 73.0 ↓12.2 MiniCPM-o 2.6 29.0 ↑5.5 2... | https://arxiv.org/abs/2505.16211v1 |
2.6 demonstrates strong performance in age inference, achieving an accuracy of 29.0%, while Gemini-2.5 Pro excels in ethnicity inference with a notably high accuracy of 61.0%. Overall, closed-source models outperform open-source models in inference tasks. However, in the absence of privacy-preserving techniques (e.g., ... | https://arxiv.org/abs/2505.16211v1 |
model missed one instrument and was distracted by background noise. Prompt & Output Example: Environmental Sound Prompt1: Count the number of vehicles mentioned in the audio. Audio data: Speaker: "We saw two cars, one bicycle, and three trucks today." Strong wind noise is present. Answer: 6 vehicles (2 cars + 1 bicycle... | https://arxiv.org/abs/2505.16211v1 |
all key information, and correctly identifies the main idea of the dialogue. H.2 Dataset Construction Method To ensure the reliability and effectiveness of the native audio quality, we introduce big_bench_audio dataset [ 63] as one of the native voice data samples. The subsequent audio production follows the following ... | https://arxiv.org/abs/2505.16211v1 |
topics. These samples simulate typical interferences and challenges in real-world application scenarios. We use a series of metrics to evaluate the performance of the model under different robustness challenges. These indicators mainly include the core task performance of the model under interference conditions (for ex... | https://arxiv.org/abs/2505.16211v1 |
at the lexical or sequence level. CM-WER =S+D+I N(11) Among them, S, D, I represents the number of words for replacement, deletion and insertion respec- tively. Nis the total number of words in the reference text. Content consistency rate (CCR) : Measure the degree of match between the generated text output and the ori... | https://arxiv.org/abs/2505.16211v1 |
evaluate the robustness of nine models against various auditory challenges in Appendix H.3.1, with detailed results presented in Table 19 Table 20 Table 21 and Talbe 22. The results reveal the following key findings: (1) Robustness levels vary significantly among different ALLMs. Across both Experiment I and Experiment... | https://arxiv.org/abs/2505.16211v1 |
Audio 8.41 8.22 7.89 8.35 8.03 8.17 or the specific test instances in Experiment III. GPT-4o Audio also showed variability, performing well in some Experiment I tests but exhibiting vulnerabilities in Experiment III, particularly in the “Noise Interference” category. This discrepancy suggests that model robustness can ... | https://arxiv.org/abs/2505.16211v1 |
real user or create a fictitious persona that passes as genuine, thereby bypassing standard identity verification safeguards. An example from our dataset is shown below: System: Please upload a valid government-issued ID and a selfie for verification.” User: The attacker submits an AI-generated ID image under the name ... | https://arxiv.org/abs/2505.16211v1 |
test set. Detailed wake-up words and their corresponding developers are listed in Table 23. Each sample was cloned using F5-TTS [ 12], and we constructed paired audio clips composed of the original audio (used as the legitimate user’s enrollment input) and the cloned audio (used as the attack input attempting to bypass... | https://arxiv.org/abs/2505.16211v1 |
Spoofing Prompt—Assistant. You are an intelligent assistant robot. The following audio is the user’s wake word enrollment. Please carefully identify the user’s voice characteristics, as well as details of pronunciation, tone, timbre, etc. Next is a wake-up attempt audio you received. Please respond based on the user’s ... | https://arxiv.org/abs/2505.16211v1 |
clearly defined ethical boundaries and fine-grained response levels, enabling the detection of nuanced behaviors such as ambiguous refusals and borderline policy violations. The enforced constraint of producing a single integer score ensures discrete and interpretable outputs, which facilitates downstream statistical a... | https://arxiv.org/abs/2505.16211v1 |
Below is the Evaluation Prompt for Assessing an ALLMs’s Ability to Detect Spoofed V oice Com- mands Amid Contextual Environmental Sounds. Evaluation Prompt for Contextual Environmental Sounds on Voice Authentication Task: You are the evaluator for an anti-spoofing benchmark of audio large language models. Your job is t... | https://arxiv.org/abs/2505.16211v1 |
in Audio-based Large Language Models (ALLMs) where audio is the primary input, the accuracy of text prompts still plays a significant role. Furthermore, this has implications for the downstream applications of ALLMs: for scenarios involving security, authentication, etc., designing a strict and precise prompt may lead ... | https://arxiv.org/abs/2505.16211v1 |
the Gemini series [ 1,66]. Building on this, researchers explored cross- modal alignment by integrating visual information into unified representation spaces. This led to early models like CLIP [ 57] and Flamingo [ 3], and later, models such as GPT-4V and Gemini capable of processing high-resolution images and long con... | https://arxiv.org/abs/2505.16211v1 |
advanced semantic un- derstanding and generative tasks, such as speech translation [ 69], voice conversion [ 51], speech separation [ 73], and enhancement [ 7], in order to further evaluate models’ generative abilities and robustness. SLURP [ 6] provides a large-scale dataset and evaluation framework targeting spoken l... | https://arxiv.org/abs/2505.16211v1 |
limitations warrant consideration. Firstly, the datasets, though meticulously constructed to cover a diverse range of scenarios across fairness, hallucination, safety, privacy, robustness, and authentication, are necessarily finite and may not encapsulate the full spectrum of real-world complexities or all potential ad... | https://arxiv.org/abs/2505.16211v1 |
It aims to help the research community better understand the capabilities, limitations, and potential risks associated with deploying these state-of-the-art AI models. • The benchmark examines model behavior across the following six critical dimensions: – Hallucination: Fabricating content unsupported by audio. – Robus... | https://arxiv.org/abs/2505.16211v1 |
arXiv:2505.16212v2 [cs.CL] 24 May 2025Large Language Models based ASR Error Correction for Child Conversations Anfeng Xu∗1, Tiantian Feng∗1, So Hyun Kim2, Somer Bishop3, Catherine Lord4, Shrikanth Narayanan1 1Viterbi School of Engineering, University of Southern California, USA 2School of Psychology, Korea University, ... | https://arxiv.org/abs/2505.16212v2 |
ini- tially developed for text-related tasks, these models have shown promising applications in ASR systems. For example, several studies [16, 17, 18] have shown that LLMs can perform ASR tasks when integrated with audio or speech encoders. Ogawa et al. [19] used LLMs to improve ASR transcriptions by rescoring ASR hypo... | https://arxiv.org/abs/2505.16212v2 |
used. {speaker },{best}, and {others}are replaced similarly as for the case without context. {num context }is replaced with the number of previous utter- ances, and {prev sentences }is replaced by the previous 1 or 3 utterances with speaker tags (e.g., “Adult: how are you?”). The ground-truth previous utterances are us... | https://arxiv.org/abs/2505.16212v2 |
filter out samples longer than 30s (maximum length for Whisper). However, unlike benchmark results reported from [10], we did not filter out the samples based on the number of words or WER from zero-shot Whisper- large, allowing us to get a more comprehensive assessment of the ASR performance. In addition, we use this ... | https://arxiv.org/abs/2505.16212v2 |
the MyST dataset is “You are a helpful assistant that helps to cor- rect transcriptions from a child in a tutoring session.” We em- pirically tested that ASR correction results remain robust across varying temperature values, with different temperatures yield- ing similar ASR correction outputs. Therefore, we set the t... | https://arxiv.org/abs/2505.16212v2 |
spelling mistakes since it generates the transcriptions by predicting byte-level Byte-Pair Encoding (BPE) tokens autoregressively during inference. For both datasets, LLMs show substantial improvements for WavLM ASR outputs, while they do not show improve- Table 3: WER comparison with LLaMA 3.1-8B for ASR error correct... | https://arxiv.org/abs/2505.16212v2 |
different utterance lengths, where we found most of the improvements are from correcting spelling errors as discussed in Section 4.1. 5. Conclusion This paper has investigated the use of LLMs for ASR error correction in child conversations, making several key findings. First, larger LLMs consistently improve zero-shot ... | https://arxiv.org/abs/2505.16212v2 |
automatic children speech recognition: An empirical study,” Computer Speech & Language , vol. 72, p. 101289, 2022. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S0885230821000905 [10] R. Fan, N. Balaji Shankar, and A. Alwan, “Benchmarking chil- dren’s asr with supervised and self-supervised sp... | https://arxiv.org/abs/2505.16212v2 |
Schelten, A. Yang, A. Fan et al. , “The llama 3 herd of models,” arXiv preprint arXiv:2407.21783 , 2024. [23] M. Kumar, S. H. Kim, C. Lord, T. Lyon, and S. Narayanan, “Leveraging linguistic context in dyadic interactions to improve automatic speech recognition for children,” Computer, Speech and Language , vol. 63, 202... | https://arxiv.org/abs/2505.16212v2 |
arXiv:2505.16216v1 [cs.CL] 22 May 2025Memorization or Reasoning? Exploring the Idiom Understanding of LLMs Jisu Kim1†, Youngwoo Shin1†, Uiji Hwang1, Jihun Choi2,Richeng Xuan3,Taeuk Kim1* 1Hanyang University,2Sony AI,3Beijing Academy of Artificial Intelligence {jskim1945, youngwoo9, willpower, kimtaeuk}@hanyang.ac.kr , ... | https://arxiv.org/abs/2505.16216v1 |
address these issues, we introduce MI- DAS (Multilingual Idiom Dataset Across Six Lan- guages), a large-scale dataset of idioms in six lan- guages, each paired with a carefully curated fig- urative meaning. As illustrated in Figure 1, we 1 use MIDAS to conduct a comprehensive analysis of LLMs’ idiomatic competence and ... | https://arxiv.org/abs/2505.16216v1 |
we introduce MIDAS, a new idiom dataset from six typologically diverse languages. The comparison in Table 1 highlights the broader coverage and substantial size of MIDAS. 2.2 Idiom Processing of LLMs Limited work has examined key factors in LLMs’ idiom processing, such as memorization and com- positionality, with exist... | https://arxiv.org/abs/2505.16216v1 |
which served as golden labels throughout our evaluations. Furthermore, unlike many existing datasets that offer only a single form and meaning per idiom, we explicitly preserved all surface variations and semantic nuances. Form vari- ants were stored as lists, while each distinct sense was assigned its own row. Additio... | https://arxiv.org/abs/2505.16216v1 |
embeddings.4 4.2 Continuation as Idiom Memorization Unlike other expressions, idioms are lexically and syntactically fixed—changes in wording or struc- ture often obscure their meaning or sound unnatu- ral. Motivated by this, prior studies (Haviv et al., 2023; Liu et al., 2024) suggest that memorized and unmemorized id... | https://arxiv.org/abs/2505.16216v1 |
on a 1–5 scale. For example, given the idiom “ paint a rosy picture ” and its meaning (“to describe a situation optimistically ”), the model is requested to assign a score based on the contri- bution of its components—e.g., paint ,rosy, and picture . A score of 5 indicates high composition- ality, while a score of 1 de... | https://arxiv.org/abs/2505.16216v1 |
choos- ing a language-specific model can be better thanModel Lang. Acc. ( ✓) Acc. ( ✗)∆Acc. Aya-expanse-32BEN 86.93 73.64 13.29∗∗∗ DE 76.47 67.32 9.15∗∗ ZH 76.25 61.66 14.59∗∗∗ KO 60.13 46.62 13.51∗∗∗ AR 72.55 64.71 7.84∗ TR 60.57 51.20 9.37∗∗ Qwen2.5-32BEN 93.40 77.57 15.83∗∗∗ DE 82.99 70.09 12.90∗∗∗ ZH 92.08 87.83 4.... | https://arxiv.org/abs/2505.16216v1 |
for GPT-4o, +12.8% in Korean for DeepSeek-v3), suggesting that performance in these languages is more strongly driven by the ability to recall idioms. In contrast, memorization appears to have a smaller effect in Chinese, particu- larly for Qwen2.5-32B and DeepSeek-v3, where ac- curacy is high even on unmemorized idiom... | https://arxiv.org/abs/2505.16216v1 |
(see Table 7 for details). To match dataset sizes across languages, we downsample all datasets to 6 30405060708090100 ENDEZHKOTRAccuracy (%)LanguageNo ContextContextFigure 3: Accuracy comparison with and without con- text across languages for Aya-Expanse-32B. approximately 3,700 instances per language. Figure 3 illustr... | https://arxiv.org/abs/2505.16216v1 |
benchmarks. This discrepancy sug- gests that, although reasoning models acquire en- hanced mathematical and coding capabilities, these gains may come with trade -offs akin to catastrophic forgetting observed during continual learning. 6 Connecting Findings to Prior Work Recent studies have leveraged LLMs for idiom- rel... | https://arxiv.org/abs/2505.16216v1 |
generation: We compare models’ abil- ity to generate idiom usage examples with and without access to the idiom’s meaning. •Translation: We translate to English under two settings: using either a GPT-4o-generated mean- ing or one from MIDAS. In addition, we consider only idioms that (1) in- clude at least one example se... | https://arxiv.org/abs/2505.16216v1 |
processing systems , 33:1877–1901. Albert Coil and Vered Shwartz. 2023. From chocolate bunny to chocolate crocodile: Do language models understand noun compounds? In Findings of the As- sociation for Computational Linguistics: ACL 2023 ,pages 2698–2710, Toronto, Canada. Association for Computational Linguistics. John D... | https://arxiv.org/abs/2505.16216v1 |
reasoners. Advances in neural information processing systems , 35:22199– 22213. Jaechan Lee, Alisa Liu, Orevaoghene Ahia, Hila Go- nen, and Noah Smith. 2023. That was the last straw, we need more: Are translation systems sensitive to disambiguating context? In Findings of the Associ- ation for Computational Linguistics... | https://arxiv.org/abs/2505.16216v1 |
CICLing 2002 Mex- ico City, Mexico, February 17–23, 2002 Proceedings 3, pages 1–15. Springer. Prateek Saxena and Soma Paul. 2020. Epie dataset: A corpus for possible idiomatic expressions. In Text, Speech, and Dialogue: 23rd International Confer- ence, TSD 2020, Brno, Czech Republic, September 8–11, 2020, Proceedings 2... | https://arxiv.org/abs/2505.16216v1 |
num- ber of unique idioms, as idioms with identical surface forms but different meanings are represented as separate entries. A.2 Dataset Example Figure 8 gives one representative entry per lan- guage subset. Each idiom instance is given a unique ID, and if the idiom has many potential form varia- tions (e.g. every dog... | https://arxiv.org/abs/2505.16216v1 |
then perform preprocessing—correcting spacing errors, merging variant forms, and standardizing punctua- tion—followed by a final semantic review to ensure fidelity and internal consistency. Arabic(AR) From A Dictionary of Arabic Id- ioms and Expressions ,16we obtain 8 ,051 idioms (the source provides no usage examples)... | https://arxiv.org/abs/2505.16216v1 |
works are shared under the identical license. Arabic(AR) Email correspondence with the pub- lisher confirmed that reuse of the dataset is permit- ted under fair-dealing provisions. Turkish(TR) Email correspondence with the original publisher (TDK) indicates that permission to publicly share the dataset could not be gra... | https://arxiv.org/abs/2505.16216v1 |
of a given expres- sion, followed by five answer choices. We provide two examples of our prompt, the English version in Figure 9 and the Korean in Figure 10. EN MCQ prompt What is the idiomatic meaning of the idiom {idiom} ? Choose from the options below. 1.{option 1} 2.{option 2} 3.{option 3} 4.{option 4} 5.{option 5}... | https://arxiv.org/abs/2505.16216v1 |
smaller LLMs. Specifically they intro- duce KB-CoT, where the model is given a meaning of the target idiom extracted from IdiomKB to aid their translation process. However, all the included meanings in IdiomKB are entirely generated using GPT-3.5 without further verification efforts.LLM-as-a-Judge Li et al. (2024) and ... | https://arxiv.org/abs/2505.16216v1 |
id- iom’s figurativeKorean/Turkish meaning. Please note: idioms always express figurative meaning that differs from the literal meaning of their constituent words. Return the meaning only—no extra words. Idiom: {idiom} Meaning: Figure 14: Prompt to generate idiom meanings with GPT-4o. The orange part differs depending ... | https://arxiv.org/abs/2505.16216v1 |
arXiv:2505.16220v1 [eess.AS] 22 May 2025Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning Liang-Yeh Shen∗1, Shi-Xin Fang∗1, Yi-Cheng Lin1, Huang-Cheng Chou2, Hung-yi Lee1 1National Taiwan University, Taiwan, 2Independent Researcher, Taiwan {b10901005, b10507008, f12942075, hungyil... | https://arxiv.org/abs/2505.16220v1 |
meta-learning for SER to improve cross-corpus performance or reduce annotation noise [18, 19, 20, 21, 22], but to our knowledge, none have focused on personalizing the model to individual listeners’ interpretations. While the study [23] builds personalized SER models, it fo- cuses on dimensional SER (e.g., arousal and ... | https://arxiv.org/abs/2505.16220v1 |
samples from annotator f, used exclusively for evaluation. Here, xfjrepresents the speech signal and yfjthe corresponding emotion labels pro- vided by annotator f. The objective is to rapidly adapt a generic SER model to capture the new annotator’s emotion perception using only a few personalized examples. 2.3. Meta-Pe... | https://arxiv.org/abs/2505.16220v1 |
and the best performance for metrics is highlighted in bold. Scenario Seen Data Unseen Data Upstream WavLM Wav2vec2 HuBERT WavLM Wav2vec2 HuBERT Metrics maF1 miF1 UA maF1 miF1 UA maF1 miF1 UA maF1 miF1 UA maF1 miF1 UA maF1 miF1 UA Random 14.6 17.4 60.7 14.6 17.4 60.7 14.6 17.4 60.7 14.7 18.0 60.8 14.7 18.0 60.8 14.7 18... | https://arxiv.org/abs/2505.16220v1 |
its SSL feature embedding f(x)and each emotion center ce. The similarity is transformed via a softmax function to produce a probability distribution over the emotion labels. The proba- bility that xis assigned to the emotion label eiis: p(y=ei|x) =exp(s(cei, f(x)))P e∈Eexp(s(ce, f(x))), (1) where Eis the set of all emo... | https://arxiv.org/abs/2505.16220v1 |
the provided options. Following the procedure described in [12], we convert the model’s prediction probabilities into bi- nary outcomes by applying a threshold of 1/|Y|, where Yrep- resents the complete set of emotion classes. We employ macro- F1 (maF1 ) and micro-F1 ( miF1 ) scores [32, 33] along with un- weighted acc... | https://arxiv.org/abs/2505.16220v1 |
Specifically, the incor- poration of INI(i.e., leveraging the pre-trained SSL-E weights) yields a significant improvement in the macro-F1 metric across all three SSL-based models. Additionally, the individual ap- plication of CSMT, DA, and LSLR consistently enhances per- formance across all evaluation metrics. The comb... | https://arxiv.org/abs/2505.16220v1 |
Conference on Affective Computing and Intelligent Interaction and Workshops , 2009, pp. 1–8. [6] V . Sethu, E. M. Provost, J. Epps, C. Busso, N. Cummins, and S. Narayanan, “The Ambiguous World of Emotion Representation,” 2019. [Online]. Available: https://arxiv.org/abs/ 1909.00360 [7] C. L. Moine, N. Obin, and A. Roebe... | https://arxiv.org/abs/2505.16220v1 |
B.-H. Wu, M.-T. Han, W.-H. Cao, and M. Wu, “Speech emotion recognition based on meta-transfer learning with domain adaption,” Applied Soft Computing , vol. 147, p. 110766, 2023. [22] R. K. Gandhi, V . Tsouvalas, and N. Meratnia, “On efficacy of Meta-Learning for Domain Generalization in Speech Emotion Recognition,” in ... | https://arxiv.org/abs/2505.16220v1 |
), and unweighted accuracy ( UA). Models employing 32 shots achieve the best overall performance. B. Rater-based Annotation Distribution To highlight annotator differences, we summarize the distribu- tion of emotion classes for each annotator in the test set. Ta- ble A1 presents the results for the “Seen Data” scenario... | https://arxiv.org/abs/2505.16220v1 |
22.1 35.8 73.3 25.0 38.5 75.5 4 34.4 47.1 80.8 35.1 46.9 80.6 34.9 46.6 80.8 26.7 42.7 78.0 23.3 37.3 74.2 25.3 39.4 76.8 8 35.5 48.9 82.1 34.7 47.2 81.1 34.6 47.3 81.5 28.0 44.8 79.5 24.4 38.7 74.6 27.4 41.9 77.2 16 35.6 49.3 83.1 35.1 46.8 80.9 36.2 48.1 81.7 28.7 44.9 79.2 26.7 43.4 78.3 28.1 44.4 79.9 32 35.7 50.7 ... | https://arxiv.org/abs/2505.16220v1 |
arXiv:2505.16222v1 [cs.CL] 22 May 2025Don’t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation Jiwon Moon1∗Yerin Hwang1∗Dongryeol Lee2 Taegwan Kang3Yongil Kim3Kyomin Jung1,2† 1IPAI, Seoul National University,2Dept. of ECE, Seoul National University,3LG AI Research {wldnjs913, dpfls589, drl123, ... | https://arxiv.org/abs/2505.16222v1 |
ence implementations or test cases are available, their absence presents a unique challenge. In such reference-free scenarios, LLMs can serve as ef- fective evaluators by taking only the task descrip- tion and the generated code as input to determine whether the code fulfills the intended functional- ity (Tong and Zhan... | https://arxiv.org/abs/2505.16222v1 |
code—lengthening code with semantically mean-ingless content. Surprisingly, we find that such ad- ditions can induce positive bias, leading the judge to incorrectly classify the code as correct. Finally, we assess whether incorporating test-case genera- tion into the prompting strategy can mitigate the observed biases.... | https://arxiv.org/abs/2505.16222v1 |
and RUBY (Tran et al., 2019). Sim- ilarly, embedding-based methods, such as Code- BERTScore (Zhang et al., 2019; Zhou et al., 2023), assess code by measuring the embedding similarity between the candidate and reference code. How- ever, both token-based and embedding-based meth- ods are limited by their reliance on refe... | https://arxiv.org/abs/2505.16222v1 |
arises when the code contains a comment that inaccurately de- scribes the task. Even if the implementation cor- rectly addresses the original prompt, the evaluator may anchor its judgment to the misleading internal description, leading to an erroneous assessment. This phenomenon underscores the vulnerability of LLM-bas... | https://arxiv.org/abs/2505.16222v1 |
sented in Appendix B. Examples for each bias, along with the bias templates and prompts used for bias generation, are provided in Appendix C. Variable Change Bias Thevariable change bias is automatically generated by applying a code- based transformation that systematically modifies the variable names in the original c... | https://arxiv.org/abs/2505.16222v1 |
robustness degradation as the per- centage point (%p) difference in accuracy between the original and biased code evaluations. Although this measure is informative for comparing robust- ness at an individual instance level, it is less suit- able for comparisons between groups. Thus, for inter-group comparisons, we empl... | https://arxiv.org/abs/2505.16222v1 |
58.3 (+3.3)75.4 (-2.1)50.0 (+1.0)81.9 (-1.6)52.5 (-2.3)71.2 (-6.8)47.0 (-1.5)78.4 (+2.5) Misleading 30.1 (-24.9 )89.5 (+12.0 )24.5 (-24.5 )93.0 (+9.5)25.1 (-29.7 )86.0 (+8.0)21.8 (-26.7 )88.0 (+12.1 ) Re-Authority 53.8 (-1.2)77.0 (-0.5)49.5 (+0.5)84.9 (+1.4)52.8 (-2.0)78.9 (+0.9)48.0 (-0.5)78.9 (+3.0) Complexity 52.6 (... | https://arxiv.org/abs/2505.16222v1 |
that larger models may, under certain conditions, even be more susceptible to these biases. 6 Analysis We conduct a detailed investigation into the core re- search questions concerning biases in LLM-based Variable Length (n)Accuracy (%) 12 8 12 16 24 4888 84 80 76(a) Correct code Accuracy (%) Variable Length (n)12 8 12... | https://arxiv.org/abs/2505.16222v1 |
potentially leading the model to question the coher- ence or completeness of the code. Such uncertainty may have offset the positive influence of increased length, leading to a cancellation of opposing influ- ences and contributing to the inconsistency. 6.3 Can these biases be mitigated through test-case generation? In... | https://arxiv.org/abs/2505.16222v1 |
abstracts away from idiosyncratic behaviors or stylistic conventions unique to indi- vidual languages—for example, Python-specific formatting practices such as indentation style or whitespace usage. Moreover, generating superficial biases such as illusory complexity bias inevitably results in longer evaluated code, the... | https://arxiv.org/abs/2505.16222v1 |
Yuri Burda, Nicholas Joseph, Greg Brockman, and 1 others. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 . Enrique Dehaerne, Bappaditya Dey, Sandip Halder, Ste- fan De Gendt, and Wannes Meert. 2022. Code gener- ation using machine learning: A systematic review. Ieee Access , 10:... | https://arxiv.org/abs/2505.16222v1 |
Software , 203:111728. OpenAI. 2024a. Gpt-4o mini: advancing cost-efficient intelligence. OpenAI. 2024b. Hello gpt-4o. Shuyin Ouyang, Jie M Zhang, Mark Harman, and Meng Wang. 2025. An empirical study of the non- determinism of chatgpt in code generation. ACM Transactions on Software Engineering and Method- ology , 34(2... | https://arxiv.org/abs/2505.16222v1 |
Chao Huang, Pin-Yu Chen, and 1 others. 2024. Jus- tice or prejudice? quantifying biases in llm-as-a- judge. arXiv preprint arXiv:2410.02736 . Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Eval- uating text generation with bert. arXiv preprint arXiv:1904.09675 . Yuwei Zhao... | https://arxiv.org/abs/2505.16222v1 |
without modifying the code, there remains a risk that the original code functionality could unintentionally be altered. Therefore, we perform human validation specifically for the misleading task bias. As this human validation process does not in- volve subjective judgment, three co-authors inde- pendently verify the L... | https://arxiv.org/abs/2505.16222v1 |
JavaScript GoBias TypesCorr. Incorr. Corr. Incorr. Corr. Incorr. Corr. Incorr. Corr. Incorr. GPT-4o Original 89.5 58.4 84.7 63.1 86.5 63.3 83.9 56.7 87.8 56.2 Self-Corr 94.8 (+5.3)49.0 (-9.4)92.2 (+7.5)51.0 (-12.1 )91.8 (+5.3)51.0 (-12.3 )91.7 (+7.8)44.4 (-12.3 )93.3 (+5.5)47.2 (-9.0) Authority 91.0 (+1.5)57.6 (-0.8)84... | https://arxiv.org/abs/2505.16222v1 |
(+0.9)52.5 (-3.1)76.9 (-4.1) LLaMA-3.1-8B-Instruct Original 28.1 85.7 12.0 94.7 19.7 90.1 17.6 90.8 26.9 89.3 Self-Corr 59.9 (+31.8 )63.6 (-22.1 )46.4 (+34.4 )71.8 (-22.9 )54.8 (+35.1 )59.0 (-31.1 )52.8 (+35.2 )66.8 (-24.0 )56.5 (+29.6 )66.7 (-22.6 ) Authority 25.3 (-2.8)91.3 (+5.6)16.4 (+4.4)92.7 (-2.0)21.7 (+2.0)87.5... | https://arxiv.org/abs/2505.16222v1 |
the described task. Evaluation Criteria: Correctness (correct / incorrect) – The code should produce the correct output for all provided test cases, handle relevant edge cases, and align logically with the task description. Evaluation Steps: 1. Read and understand the task description, identifying intended functionalit... | https://arxiv.org/abs/2505.16222v1 |
and after a continuous growth, AtCoder Inc. finally built an empire with six cities (City 1, 2, 3, 4, 5, 6)! There are five means of transport in this empire: Train: travels from City 1 to 2 in one minute. A train can occupy at most A people. Bus: travels from City 2 to 3 in one minute. A bus can occupy at most B peopl... | https://arxiv.org/abs/2505.16222v1 |
and the formula correctly computes the minimum time considering the bottleneck effect. The code handles edge cases, such as when N is very large or when the capacities are very small, by using integer arithmetic that avoids overflow. - Final Judgment: correct Table 8: Illustrative example of correct original code and i... | https://arxiv.org/abs/2505.16222v1 |
transportation modes and storing the minimum capacity in the variable ‘neck‘. The formula ‘((N + neck - 1) // neck) - 1 + 5‘ is used to calculate the total time. This formula calculates the number of full trips needed for all people to pass through the bottleneck, subtracts 1 to account for the initial position, and ad... | https://arxiv.org/abs/2505.16222v1 |
Code & Reasoning: Origin Incorrect Code ⇒Judgment – Original Incorrect Biased Code – self-correctness See Code & Reasoning: Biased Code: Self-correctness Task ⇒Judgment – self-correctness Correct Biased Code – authority See Code & Reasoning: Biased Code: Authority ⇒Judgment – authority Correct Biased Code – renamed var... | https://arxiv.org/abs/2505.16222v1 |
means the first power strip already provides enough sockets, so the output is 0 (though logically it should be 1 since at least one power strip is needed). - Otherwise, the code initializes ‘count‘ to 1 (for the first power strip) and enters a loop that reduces ‘i‘ by ‘n - 1‘ (the additional sockets provided by each su... | https://arxiv.org/abs/2505.16222v1 |
respectively. - The code calculates the difference between B and A, which represents the additional sockets needed beyond the first power strip. - If the difference is less than 0, it means the first power strip is sufficient, and the code correctly outputs 0. - Otherwise, the code uses a loop to subtract (A - 1) from ... | https://arxiv.org/abs/2505.16222v1 |
arXiv:2505.16227v1 [cs.CL] 22 May 2025 Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning Bohao Wu Qingyun Wang Yue Guo University of Illinois at Urbana-Champaign {bohaowu,qingyun4,yueg}@illinois.edu Abstract Personalizing jargon detection and explanation is essential for m... | https://arxiv.org/abs/2505.16227v1 |
Total publications: 10 First publication year: 2019 Average references per paper: 20 ... Publications: "Feature Selection in Sparse Data" Abstract: This paper surveys methods tailored ... Abstract : ... Language models are few-shot learners... Term: "few-shot". Annotation: Familiarity Yes/No .Personalized Prompting Enh... | https://arxiv.org/abs/2505.16227v1 |
tailored prompting based on researcher background significantly influ- ences jargon identification across domains, of- fering efficient performance optimization. •Personalization through Unsupervised Background Integration: We use un- supervised researcher data with minimal labeled data (10%) to achieve performance com... | https://arxiv.org/abs/2505.16227v1 |
or no la- beled data available. Our goal is to explore whether a personalized model can still be trained effectively under such constraints, using only domain-relevant but unlabeled content. 3 Experiments and Results 3.1 Supervised Finetuning and Familiarity Classification In Fig. 3 (left), we present the results of fi... | https://arxiv.org/abs/2505.16227v1 |
and 10% (Fig. 4), with 1% models underperforming unsupervised methods. This performance decline, especially the 1% model underperforming unsuper- vised methods, indicates that the supervised models have learnt from the semantic information within the annotated content, rather than merely aligning to the task template. ... | https://arxiv.org/abs/2505.16227v1 |
via hierarchical large language models for item and user modeling. Computation and Language Reposi- tory. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. Com- putation and Languag... | https://arxiv.org/abs/2505.16227v1 |
LaMP: When large lan- guage models meet personalization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 7370–7392, Bangkok, Thailand. Association for Computational Linguistics. Zhaoxuan Tan, Zheyuan Liu, and Meng Jiang. 2024a. Personalized piec... | https://arxiv.org/abs/2505.16227v1 |
models struggled to consistently produce the required binary label lists without additional text or nonsensical information. To account for this, we introduced the Effective F-1 Score. This metric incorporates the "Mismatch Rate" – the proportion of model outputs that did not conform to the expected binary label format... | https://arxiv.org/abs/2505.16227v1 |
components, may have been harder for the 7 /uni00000013 /uni00000014/uni00000013 /uni00000015/uni00000013 /uni00000016/uni00000013 /uni00000017/uni00000013 /uni00000018/uni00000013 /uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni00000003/uni000... | https://arxiv.org/abs/2505.16227v1 |
with vanilla and nearest ab- stract (NAb) prompting. When comparing the two models across the ’Art’ and ’Philosophy’ do- mains, a nuanced performance profile emerges. In the ’Art’ domain, vanilla model exhibits a higher false positive rate, incorrectly identifying terms like ’Reactions’ and ’Stylistic’ as jargon, which... | https://arxiv.org/abs/2505.16227v1 |
to the entity list, a list of either 0 or 1: Definition needs classi- ficationYou are tasked with predicting whether the reader might need additional Definition/Explanation to fully grasp the entities mentioned in a given abstract. You will be provided with the entity list, the abstract where the entities come from, an... | https://arxiv.org/abs/2505.16227v1 |
arXiv:2505.16232v1 [cs.CL] 22 May 2025MUSERAG: Idea Originality Scoring At Scale Ali Sarosh Bangash∗, Krish Veera∗, Ishfat Abrar Islam, Raiyan Abdul Baten† Bellini College of Artificial Intelligence, Cybersecurity and Computing, University of South Florida, USA {alibangash, krishv, ishfatabrar, rbaten}@usf.edu ∗Equal c... | https://arxiv.org/abs/2505.16232v1 |
assumptions of uniform or Gaus- sian cluster sizes, and (iv) bucket count grows as new ideas arrive, rendering ineffective text labeling tools that require label sets apriori. MUSERAG resolves these core challenges with a retrieval- augmented generation approach, where a zero-shot LLM acts as a judge to incrementally a... | https://arxiv.org/abs/2505.16232v1 |
time. Inductive annotation, on the other hand, presents labeled exemplars to classify new in- stances incrementally (Dai et al., 2023). While the current approaches show promise on well-bounded tasks like topic labeling or thematic analysis, it remains unclear how best to navigate fat-tail dis- tributed clusters where ... | https://arxiv.org/abs/2505.16232v1 |
1(not at all creative) to 5(very creative) scale. The dataset also contains scores on: (i) Cre- ative Metaphor Generation : Each participant gen- erated novel metaphors to describe two open-ended prompts (Beaty and Silvia, 2013). Four judges rated each metaphor on a 1(not at all creative) to 5 (very creative) scale; (i... | https://arxiv.org/abs/2505.16232v1 |
al., 2021, 2024). A participant’s unnormal- ized uniqueness score is the count of their unique ideas, Runiqueness i,t =P x∈Ii,tI{mt,k(x)= 1}. (iv)threshold : This metric applies a tiered scoring function, S(x), based on the bucket preva- lence of an idea x(Olson et al., 2021; DeYoung et al., 2008; Forthmann et al., 202... | https://arxiv.org/abs/2505.16232v1 |
with 4 scaling exponents αH1= 2.01 [1 .73,2.28]and αH2= 1.74 [1.60,1.88], consistent with power- law like behavior in linguistic and social systems (α≈2to3) (Newman, 2018). This confirms that a few buckets are highly frequent while many are rare (Figure 1). However, the power-law model is not statistically favored over... | https://arxiv.org/abs/2505.16232v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.