text
string
source
string
task performance of other editing methods after incorporating LyapLock, following the sequential editing of 10,000 samples on the ZsRE dataset using the LLAMA3 model. 18 Table 4: The editing performance with different hyperparameters α. Here, the abbreviations Eff.(Efficacy), Gen. (Generaliza- tion), Spe. (Specificity)...
https://arxiv.org/abs/2505.15702v1
English . . . LyapLockDanielle Darrieux’s mother tongue is English , as she was born in the United States of America, but she grew up speaking Spanish, her mother’s native language. . . 20 Table 6: Model Editing Case Study on GPT-J Model Editing Case Study on GPT-J Editing Prompt Percy Snow, the Edit Target goaltender ...
https://arxiv.org/abs/2505.15702v1
arXiv:2505.15710v1 [cs.CL] 21 May 2025Advancing LLM Safe Alignment with Safety Representation Ranking Tianqi Du1∗Zeming Wei2∗Quan Chen2∗Chenheng Zhang1Yisen Wang1,3† 1State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University 2School of Mathematical Sciences, Peki...
https://arxiv.org/abs/2505.15710v1
there exists an important twist: Traditional reward models are trained on the final generated text, often focusing on general measures of quality or alignment. In contrast, our proposed SRR explicitly targets safety by learning directly from the LLM’s latent features. Existing external reward models may miss fine-grain...
https://arxiv.org/abs/2505.15710v1
negligible impact on normal task performance. 2 Related Work LLM Safe Alignment . The issue of ensuring safe alignment in LLMs has become a longstanding challenge critical to their trustworthy deployment [ 1,15,41]. Specifically, LLMs have shown a tendency to generate harmful responses when confronted with malicious re...
https://arxiv.org/abs/2505.15710v1
candidate lists for training, we sample the base LLM multiple times using stochas- tic decoding with moderate temperature. This yields a diverse set of mplausible responses {resp1, . . . , respm}. for each instruction. We remove duplicates and include both benign and adversarial candidates by injecting jailbreak prompt...
https://arxiv.org/abs/2505.15710v1
there are ksafe responses among the m, we set p∗ i= 1/kfor each safe response with yi= 1and0for unsafe ones with yi= 0. Then we minimize the Kullback–Leibler divergence: DKL(p∗∥ˆpi) =mX i=1p∗ ilogp∗ i ˆpi(4) This loss, as a standard choice [ 23,19], encourages the model to assign high probability to safe candidates. In...
https://arxiv.org/abs/2505.15710v1
training dataset, and the rest is used as the testing dataset. For each prompt in a dataset, we sample answers from the base model using In-context Attack and In-context Defense, each 20 times. After sampling, we check whether the answers are valid by examining the keywords in them. For safe answers, we examine "Sorry"...
https://arxiv.org/abs/2505.15710v1
can effectively identify and prioritize safe responses regardless of the dataset’s specific characteristics or the types of adversarial prompts it contains. The results in Table 2 show that our SRR framework achieves consistently strong cross-dataset performance across all three LLMs (Qwen, Mistral, and Vicuna). When t...
https://arxiv.org/abs/2505.15710v1
conducted experiments on the BBQ dataset. This dataset is designed to evaluate the model’s ability to avoid generating responses that may contain biases or unfair content. The results are presented in Table 4. The results indicate that SRR achieves moderate accuracy in identifying and mitigating biased or unfair respon...
https://arxiv.org/abs/2505.15710v1
rather than classifying simulated harmful or safe responses. We also consider practical jailbreak attacks to demonstrate the robustness of SRR. The baseline in this experiment is "first accuracy", which means choosing the answer with the highest possibility generated by the base model. The results shown in Table 5, 6, ...
https://arxiv.org/abs/2505.15710v1
While it generalizes well across multiple safety benchmark datasets, its adaptability to special-domain safety scenarios requires further testing. Also, SRR’s effectiveness partly relies on the LLM generating diverse candidate responses; if the responses lack diversity, SRR’s performance may be somewhat affected. Despi...
https://arxiv.org/abs/2505.15710v1
Measuring mathematical problem solving with the math dataset. In Advances in Neural Information Processing Systems , 2021. 9 [12] Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. The curious case of neural text degeneration. In International Conference on Learning Representations , 2020. 3 [13] Ari Holtzm...
https://arxiv.org/abs/2505.15710v1
Agarwal, Jonathan Berant, and Aviral Kumar. Rewarding progress: Scaling automated process verifiers for llm reasoning. arXiv preprint arXiv:2410.08146 , 2024. 3 [27] Oscar Skean, Md Rifat Arefin, Yann LeCun, and Ravid Shwartz-Ziv. Does representation matter? exploring intermediate layers in large language models. arXiv...
https://arxiv.org/abs/2505.15710v1
Yue Wu, Kangping Xu, and Quanquan Gu. General preference modeling with preference representations for aligning language models. arXiv preprint arXiv:2410.02197 , 2024. 3 [44] Yihao Zhang, Zeming Wei, Jun Sun, and Meng Sun. Adversarial representation engineering: A general model editing framework for large language mode...
https://arxiv.org/abs/2505.15710v1
TURNABOUT LLM: A Deductive Reasoning Benchmark from Detective Games Yuan Yuan *Muyu He *Muhammad Adil Shahid Jiani Huang Ziyang Li Li Zhang University of Pennsylvania Drexel University {yyuan86|muyuhe}@upenn.edu {harry.zhang}@drexel.edu Abstract This paper introduces TURNABOUT LLM , a novel framework and dataset for ev...
https://arxiv.org/abs/2505.15712v1
knack for completely changing the direction of a trial, against all odds. 1 Dataset Sym. SLC LAS Nat. MH Het. BIG-Bench Hard ✗ ✗ ✗ ✓ ✓ ✗ LogicQA ✗ ✗ ✗ ✓ ✓ ✗ ReClor ✗ ✗ ✗ ✓ ✓ ✗ ZebraLogic ✗ ✗ ✓ ✓ ✓ ✗ ProofWriter ✓ ✗ ✗ ✗ ✓ ✗ FOLIO ✓ ✗ ✗ ✓ ✓ ✗ ProntoQA ✓ ✗ ✗ ✗ ✗ ✗ LogicBench ✓ ✗ ✗ ✗ ✗ ✗ TurnaboutLLM ✓ ✓ ✓ ✓ ✓ ✓ Table 1: Q...
https://arxiv.org/abs/2505.15712v1
In contrast, several benchmarks explicitly tar- get deductive reasoning capacities. LogiGLUE (Luo et al., 2024) integrates 24 reasoning-focused datasets into a unified benchmark. LogiQA (Liu et al., 2020) and ReClor (Yu et al., 2020) draw logical reasoning questions from standardized ex- ams like the LSAT in multi-choi...
https://arxiv.org/abs/2505.15712v1
context size limitation. However, their answer spaces remain relatively constrained. To the best of our knowledge, there is no existing benchmark that leverages the detective story format to com- bine symbolic annotations with reasoning tasks characterized by large contexts and answer spaces. A comprehensive overview o...
https://arxiv.org/abs/2505.15712v1
mostly faithful to the original games, we made various types of mod- ification (change of wording, removing turns with loose contradictions, adding information for logic leaps, etc.) to ensure the rigorousness of reasoning. 3.2 Annotations To improve rigorousness of evaluation and enable fine-grained insights into TURN...
https://arxiv.org/abs/2505.15712v1
point in the game to form a single prompt, and we prompt the model one-time for a single turn. The model is asked to give the indices of the contradicting evidence and testimony. As there may be multiple contradicting 4 Statistics AA123 AA456 GAA12 AAI12 DGRP1 Overall # Data points 85 72 43 69 37 306 Avg. context lengt...
https://arxiv.org/abs/2505.15712v1
corresponding evidence description. Second, we use a one-shot, Chain-of-Thought (CoT) prompt with an average of 2,280 words, which uses an example to direct the model to think before answering the question. Besides the use of a one-shot example, the prompt adds a “let’s think step by step” instruction at the end of the...
https://arxiv.org/abs/2505.15712v1
(DS-R1-8B) models,the OpenAI family including GPT-4.1 (G4.1), GPT- 4.1-mini (G4.1-M) and the reasoning models o3- mini (O3-M) and o4-mini (O4-M), the Llama-3.1- instruct family including Llama-70B (L3.1-70B) and Llama-8B (L3.1-8B), and the reasoning model QwQ-32B (Q-32B) exceling in reasoning and cod- ing. Except for O...
https://arxiv.org/abs/2505.15712v1
de- spite using far fewer reasoning tokens than Q-32B, G4.1 achieves approximately equal accuracy, ex- hibiting superior reasoning efficiency under a lim- ited token budget. This could further corroborate with the conjecture that intentional exploration of the answer space is more decisive to model perfor- mance than e...
https://arxiv.org/abs/2505.15712v1
But her testimony says she only saw her father . Therefore, Evidence 25 contradicts Testimony 3 because Ahlbi's account suggests Nayna was in the courtyard around 2 PM, which Rayfa did not report seeing. Validation 1418 Reasoning Tokens 111 Reasoning Tokens Figure 8: A qualitative comparison between DeepSeek-R1 and GPT...
https://arxiv.org/abs/2505.15712v1
LLM will serve as a stepping-stone toward LLMs that can navigate the messy, open-world logic of real human discourse. 8 7 Limitation Despite its breadth, TURNABOUT LLM still faces several constraints. First, its detective-courtroom focus targets contradiction spotting, leaving other deductive settings—such as scientifi...
https://arxiv.org/abs/2505.15712v1
arXiv:2209.00840. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring massive multitask language under- standing. Preprint , arXiv:2009.03300. Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark, and Yejin Ch...
https://arxiv.org/abs/2505.15712v1
Lam, Eric Chu, Eric Tang, Erkut Erdem, Ernie Chang, Ethan A. Chi, Ethan Dyer, Ethan Jerzak, Ethan Kim, Eunice En- gefu Manyasi, Evgenii Zheltonozhskii, Fanyue Xia, Fatemeh Siar, Fernando Martínez-Plumed, Francesca Happé, Francois Chollet, Frieda Rong, Gaurav Mishra, Genta Indra Winata, Gerard de Melo, Ger- mán Kruszews...
https://arxiv.org/abs/2505.15712v1
San- jeev Kwatra, Sarah A. Rous, Sarik Ghazarian, Sayan Ghosh, Sean Casey, Sebastian Bischoff, Sebastian Gehrmann, Sebastian Schuster, Sepideh Sadeghi, Shadi Hamdan, Sharon Zhou, Shashank Srivastava, Sherry Shi, Shikhar Singh, Shima Asaadi, Shixi- ang Shane Gu, Shubh Pachchigar, Shubham Tosh- niwal, Shyam Upadhyay, Shy...
https://arxiv.org/abs/2505.15712v1
the shar- ing and adaptation of the material, provided that ap- propriate attribution is given to the original source, a link to the license is provided, and that if the ma- terial is remixed, transformed, or built upon, the contributions are distributed under the same or a compatible license. Our intended use of this ...
https://arxiv.org/abs/2505.15712v1
are King heart, King diamond, King spade, Ace club, Ace heart. Chip Photo E2 Near side: 4 small + 1 big Assumption 2 [ E2]The total value is the sum of two sides .Proposition 1 Two people cannot both be winning Contradiction … … …Contradiction Reasoning Chain (Labeled) Olga Orly Dard dealer at casino, place of murder F...
https://arxiv.org/abs/2505.15712v1
arXiv:2505.15715v1 [cs.CL] 21 May 2025Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling He Hu1,2*, Yucheng Zhou3*, Juzheng Si4, Qianning Wang5, Hengheng Zhang2 Fuji Ren6, Fei Ma2†, Laizhong Cui1,2† 1College of Computer Science and Software Engineeri...
https://arxiv.org/abs/2505.15715v1
Reasoning? Therapy? Diagnostic? Dialogues SweetieChat (Ye et al., 2025) Multi-turn ✗ ✗ ✗ 3,757 ESD (Zhang et al., 2024b) Multi-turn ✗ ✗ ✗ 2,900 CPsyCounD (Zhang et al., 2024a) Multi-turn ✗ ✓ ✗ 3,134 ChatCounselor (Liu et al., 2023a) Single-turn ✗ ✗ ✗ 8,187 OpenR1-Psy (Ours) Single + Multi-turn ✓ ✓ ✓ 19,302 Table 1: Com...
https://arxiv.org/abs/2505.15715v1
lacking therapeutic modeling or con- versational depth. Subsequent work addressed multi-turn interaction: SMILE (Qiu et al., 2024a) used ChatGPT to expand single replies into coher- ent dialogues, while SoulChat (Chen et al., 2023) fine-tuned LLMs for better emotional adaptation across turns. SweetieChat (Ye et al., 20...
https://arxiv.org/abs/2505.15715v1
a parsing and planning process inspired by psycho- logical counseling techniques. This process uses a large language model (LLM), guided by a frame- work that simulates a counselor’s initial assessment and planning upon receiving a client’s self-report. For each Reddit post, the LLM performs the follow- ing analyses: (...
https://arxiv.org/abs/2505.15715v1
generate a deep reasoning trace, which is then used to construct the final counselor response. 3.4 Response Generation with Diagnostic Standard & Therapeutic Strategy Given a patient utterance UP∈ UP(and potentially preceding dialogue context C), our system gener- ates a clinically grounded counselor response UC. Unlik...
https://arxiv.org/abs/2505.15715v1
patient utter- ances UPwith their corresponding generated rea- soning traces Rand counselor responses UC. To en- sure the clinical relevance, logical consistency, and overall quality of this data for fine-tuning PsyLLM, we implement a rigorous validation process. This validation employs a multi-dimensional filtering me...
https://arxiv.org/abs/2505.15715v1
that reasoning and the input. The training objective is to maximize the likeli- hood of generating the target sequence (R, U C) given (C, U P)by minimizing the cross-entropy loss over the target tokens. Formally, the model parameters θare optimized by minimizing: L(θ)=−1 NNX i=1|RiUC,i|X t=1logPθ(yi,t|Ci, UP,i, yi,<t) ...
https://arxiv.org/abs/2505.15715v1
Performance Comparison To evaluate PsyLLM’s effectiveness against state- of-the-art models, we conducted a turn-based dia- logue evaluation on the OpenR1-Psy test set. We compared PsyLLM against baselines including ChatCounselor (Liu et al., 2023b), CPsyCounX (Zhang et al., 2024a), DeepSeek-V3 (DeepSeek-AI et al., 2024...
https://arxiv.org/abs/2505.15715v1
baselines, achieving the highest scores across all four dimensions and the Normalized Average (0.601). It demonstrates PsyLLM’s superior ability to generate human- preferred and clinically counseling responses. 4.4 Analysis Impact of Model Scale. To understand how the size of the underlying language model affects coun-...
https://arxiv.org/abs/2505.15715v1
of evaluators: five psychology graduate students (“Human”) and the Gemini model (“Auto- matic Evaluation”). Both groups scored the same set of PsyLLM-generated reasoning traces on five dimensions: Empathy, Clarity, Justification, Co- herence, and Structure. Table 7 shows the average scores from each evaluator group. Hu...
https://arxiv.org/abs/2505.15715v1
Jimena Thomann. 2006. Systematic treatment selection and prescriptive therapy.Louis G Castonguay, Catherine F Eubanks, Marvin R Goldfried, J Christopher Muran, and Wolfgang Lutz. 2015. Research on psychotherapy integration: Build- ing on the past, looking to the future. Psychotherapy Research , 25(3):365–382. Keqi Chen...
https://arxiv.org/abs/2505.15715v1
Li, He Cao, Tianhe Ren, Zeyi Liao, and Jiamin Wu. 2023b. Chatcounselor: A large language models for mental health support. CoRR , abs/2309.15461. Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John B. Torous, and Ling Chen. 2025. A survey of large language models in psychotherapy: Current...
https://arxiv.org/abs/2505.15715v1
2022. Chain-of-thought prompting elicits reasoning in large language models. In Ad- vances in Neural Information Processing Systems 35: Annual Conference on Neural Information Process- ing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022 . Jingran Xie, Shun Lei, Yue Yu, Yang Xiang, Hui W...
https://arxiv.org/abs/2505.15715v1
Chatbots The growing demand for accessible and scalable mental health support has fueled the development of AI-driven dialogue systems capable of offer- ing emotional and psychological assistance (Ge et al., 2025). Early efforts in this area primarily centered on single-turn, empathy-oriented response generation. For i...
https://arxiv.org/abs/2505.15715v1
has emerged as a challenging yet crucial frontier. Maintaining coherence, adaptability, and emotional sensitivity across multiple conversational turns introduces new demands. To address this, (Shu et al., 2025) refor- mulates CoT prompting as a dialogue between rea- soning agents and applies reinforcement learning to i...
https://arxiv.org/abs/2505.15715v1
prompt of Data Evaluation on OpenR1-Psy. 17 Figure 11: The prompt of Performance Evaluation on PsyLLM. 18 Figure 12: The prompt of Thinking Evaluation on PsyLLM. Perspective Criterion Score Subtotal Comprehensiveness1.1Accurate Empathy for Core Emotions : Does the response accurately identify and validate the client’s ...
https://arxiv.org/abs/2505.15715v1
Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities Xiaoyu Luo1,2, Yiyi Chen1, Johannes Bjerva1, Qiongxiu Li2* 1Department of Computer Science,2Department of Electronic Systems Aalborg University, Copenhagen, Denmark {xilu,yiyic,jbjerva}@cs.aau.dk,qili@es.aau.dk Abstract We present t...
https://arxiv.org/abs/2505.15722v1
dynamics that are poorly understood. Together, these challenges raise important questions that motivate our inves- tigation. For example, to what extent does mem- orization in MLLMs correspond to training data volume, as suggested by long-tail distribution as- sumptions? How might cross-lingual relationships influence ...
https://arxiv.org/abs/2505.15722v1
tions for cross-lingual transfer has shifted from word embeddings (Mikolov et al., 2013; Ammar et al., 2016; Vuli ´c et al., 2019) to contextual em- beddings (Conneau et al., 2019; Devlin et al., 2019; Raffel et al., 2020). Previous work investigat- ing cross-lingual transferability mainly leverages downstream task per...
https://arxiv.org/abs/2505.15722v1
re- laxed version of memorization that evaluates the predicted suffix against the ground truth suffix us- ing approximate string matching metrics rather than exact match. We use BLEU (Papineni et al., 2002) and Rouge-L (Lin, 2004) as our Relaxed Memorization Scores (RM) , serving as continuous indicators of memorizatio...
https://arxiv.org/abs/2505.15722v1
hin a MLLM, we measure the pair-wise language similarity for a language pair {l1, l2}, where l1, l2∈Lusing cosine similarity between language-specific embeddings: cos (sl1,sl2) =sl1·sl2 ||sl1|| · ||sl2||. Empirically, we find that the language similarity drawn from the final layer embeddings of MLLMs shows a stronger c...
https://arxiv.org/abs/2505.15722v1
weighted by language promi- nence (node degrees) and normalized by global edge weights to preserve topological information. Specifically, for a subgraph G′= (V′,E′), whereeach node i∈ V′has features ti(tokens) and mi (memorization), we define the subgraph-level rep- resentations as: ¯t=X i∈V′ niP j∈V′nj·ti! where ni=|{...
https://arxiv.org/abs/2505.15722v1
architec- tures, prompt length and model scale. In each di- mension, we measure the Memorization Rates (cf. Section 3) and correlate with training data (in to- ken counts) in languages, using both the Pearson correlation ( r) and Graph-based Correlation ( ρG) metrics.Mem. Metric r ρ G EM -0.13 -0.24 PM -0.36 -0.56 RM (...
https://arxiv.org/abs/2505.15722v1
transferability among similar languages plays an essential role in memorization in MLLMs. 6.4 Memorization across Model Architectures & Scales Since language similarity is model-specific, its scores exhibit different distributions across models. We select the specific threshold θto better incorpo- rate structural patte...
https://arxiv.org/abs/2505.15722v1
100 0.50 -35.0 – – 150 0.90 −31.4 – – MT5-L ARGE50 0.02 -78.4 – – 100 0.23 -52.6 – – 150 0.49 −39.0 – – Table 4: Memorization Rates across various prompt lengths (35,85,135), model architectures, and model scales. The predicted token length is fixed at 15. The highest memorization rates for each model are bold .Takeawa...
https://arxiv.org/abs/2505.15722v1
tion in MLLMs, grounding observed memorization patterns through language similarity and revealing cross-linguality as a key factor shaping memoriza- tion in MLLMs. To this end, we define memo- rization metrics tailored to language models and propose a graph-based correlation measure that in- corporates language similar...
https://arxiv.org/abs/2505.15722v1
Liu, Úlfar Erlingsson, Jernej Kos, and Dawn Song. 2019. The secret sharer: Eval- uating and testing unintended memorization in neu- ral networks. In 28th USENIX security symposium (USENIX security 19) , pages 267–284. Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-V oss, Katherine Lee,...
https://arxiv.org/abs/2505.15722v1
tail via influence estimation. 33:2881–2891. Yinghua Gao, Yiming Li, Linghui Zhu, Dongxian Wu, Yong Jiang, and Shu-Tao Xia. 2023. Not all sam- ples are born equal: Towards effective clean-label backdoor attacks. Pattern Recognition , 139:109512. Isha Garg, Deepak Ravikumar, and Kaushik Roy. 2023. Memorization through t...
https://arxiv.org/abs/2505.15722v1
Kevin Hef- fernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault,Gabriel Mejia Gonzalez, Prangthip Hansanti, and 20 others. 2024. Scaling neural machine translation to 200 languages. Nature , 630(8018):841–846. Kishore Papineni...
https://arxiv.org/abs/2505.15722v1
statistical relational learn- ing and its connections to other fields (SRL 2004) , pages 132–137. 12 A Language-specific Subspaces The algorithm for identifying language-specific subspace is as in Algorithm 1, refer to Xie et al. (2024) for more details. Algorithm 1: Language-specific Subspace Identification 1Input : L...
https://arxiv.org/abs/2505.15722v1
0.44 Table 8: Cross-topology vs. intra-topology Pearson cor- relation at varying thresholds for MGPT-13B. Threshold θ MT5-SMALL 0.54 0.56 0.58 0.60 0.62 0.64 0.66 0.68 #Subgraph 30 38 46 52 56 66 72 77 #Single Point 16 23 29 36 41 57 61 70 EM Intra 0.27 0.27 0.26 0.24 0.20 0.22 0.16 0.12 EM Cross -0.14 -0.06 -0.03 -0.0...
https://arxiv.org/abs/2505.15722v1
. Figure 8: Layer-wise trend for ASJP (UMAP) . 14 B.5 Examples of Exact Memorization Danish MGPT-101 Prompt: Americas Best Value Inn Santa Rosa tilbyder også mange faciliteter der vil berige dit ophold i Santa Rosa (CA). Hotellet tilbyder sine gæster adgang til et stort udvalg af servicetilbud, som trådløst internet i ...
https://arxiv.org/abs/2505.15722v1
that safety and dignity are <extra_id_4> ed,” the report says. The announcement proposes an investment Reference: <extra_id_0> for people <extra_id_1> ’s disease and <extra_id_2> “Supporting people <extra_id_3> givers <extra_id_4> maintain Prediction: <extra_id_0> for people <extra_id_1> ’s disease and <extra_id_2> “Su...
https://arxiv.org/abs/2505.15722v1
arXiv:2505.15727v1 [cs.CL] 21 May 2025VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models Heyang Liu1,2∗Yuhao Wang1,2∗Ziyang Cheng3Ronghua Wu2Qunshan Gu2 Yanfeng Wang1Yu Wang1† 1Shanghai Jiao Tong University2Ant Group3Wuhan University {liuheyang, colane, wangyanfeng622, yuwangsjtu}...
https://arxiv.org/abs/2505.15727v1
understanding but also in producing speech responses with natural acoustic qualities, fluent and efficient conversations, and robustness against noisy or adverse acoustic environments. Current speech evaluation benchmarks (Yang et al., 2024; Chen et al., 2024b; Li et al., 2025) suffer from crit- ical limitations: (1) e...
https://arxiv.org/abs/2505.15727v1
set. In terms of robustness evaluation, V ocalBench refers to V oiceBench (Chen et al., 2024b) and conducts experiments on two types of noise, reverberation, far-field, packet loss, and clipping distortion. In order to achieve more detailed ability assess- ment, we also provide multi-granular annotations, such as topic...
https://arxiv.org/abs/2505.15727v1
have disassembled the pronunciation of the word or modified it to a homo- phone for synthesis until it matches the correct pro- nunciation. For evaluation sets with additional re- quirements, extra examination has been introduced. For example, in the construction of the emotion- aware set, speech emotion recognition wi...
https://arxiv.org/abs/2505.15727v1
the text modality, and the lack of widely adopted speech test has prevented the development of this field. We have selected 8 common reasoning types, including analogical, causal, common sense, conflicts, deductive and in- ductive, hypothesis, math, and story analysis. The instances are transformed into the spoken form...
https://arxiv.org/abs/2505.15727v1
response and serve as the clean data for robustness testing. 3.3.2 Multi-round In the conversational setting, the modeling of con- text information dramatically affects the response quality. To evaluate the multi-round chat ability of speech interaction models, we have reconstructed 400 test instances from mt-bench-101...
https://arxiv.org/abs/2505.15727v1
the emotional query. The overall emotion-aware score is added with the acoustic score and the semantic score in the s2s setting. 5 3.3.5 Safety Alignment Safety alignment ensures the behaviour is consis- tent with human values, ethical norms, and safety standards. We have selected 400 instances for safety testing2, cov...
https://arxiv.org/abs/2505.15727v1
in Table 4. The pur- pose of constructing this indicator is to facilitate model developers in carrying out corresponding improvements based on the defects of the model. Qwen2.5-Omni surpasses on four topics, V ocalNet- 8B outperforms on five topics, and MiniCPM-o wins six first places. Qwen2.5-Omni shows its superiorit...
https://arxiv.org/abs/2505.15727v1
preserve the potential to emerge as a writing assistant. 4.3 Acoustic On UTMOS calculations, experiments show that the speech quality of speech models is better than that of omni models. The naturalness and flu- ency of tiny models are generally outstanding, in- dicating sufficient speech generation capabilities. Both ...
https://arxiv.org/abs/2505.15727v1
com- pare the response style and empathy performance. In terms of safety alignment, most models achieve high scores, among which SLAM-Omni and V ocalNet-8B are relatively safe and can reject more than 90% of dangerous questions. LLaMA- Omni is the only model that fails major tests, re- jecting only 27.75% of the exampl...
https://arxiv.org/abs/2505.15727v1
Deng, Zhihao Du, Changfeng Gao, Zhifu Gao, Yue Gu, Ting He, Hangrui Hu, Kai Hu, and 1 others. 2024. Funaudi- ollm: V oice understanding and generation foundation models for natural interaction between humans and llms. arXiv preprint arXiv:2407.04051 . Philip Anastassiou, Jiawei Chen, Jitong Chen, Yuanzhe Chen, Zhuo Che...
https://arxiv.org/abs/2505.15727v1
preprint arXiv:2504.18425 . Xinrun Du, Yifan Yao, Kaijing Ma, Bingli Wang, Tianyu Zheng, King Zhu, Minghao Liu, Yiming Liang, Xiaolong Jin, Zhenlin Wei, and 1 others. 2025. Supergpqa: Scaling llm evaluation across 285 gradu- ate disciplines. arXiv preprint arXiv:2502.14739 . Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu...
https://arxiv.org/abs/2505.15727v1
on Audio, Speech, and Language Processing , 24(2):378– 387. Xuechen Li, Tianyi Zhang, Yann Dubois, Rohan Taori, Ishaan Gulrajani, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Alpacaeval: An au- tomatic evaluator of instruction-following models. https://github.com/tatsu-lab/alpaca_eval . Yadong Li, Ju...
https://arxiv.org/abs/2505.15727v1
Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, MA Zejun, and Chao Zhang. 2024. Salmonn: Towards generic hearing abilities for large language models. In The TwelfthInternational Conference on Learning Representa- tions . Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo, Xiong Wang, Jincenzi Wu, Dongchao Yang, ...
https://arxiv.org/abs/2505.15727v1
GLM-4- V oice (Zeng et al., 2024) and Baichuan-Omni (Li et al., 2025). Another type, aligned multimodal models, perform text and speech decoding with distinct heads to maintain the abilities of the LLM backbone. Most speech interaction models follow this paradigm, including Mini-Omni(2) (Xie and Wu, 2024a,b), LLaMA-Omn...
https://arxiv.org/abs/2505.15727v1
Chat Robustness AIR-Bench (Yang et al., 2024) ✘ 10 ✘ ✘ ✘ ✘ Speech Understanding SD-Eval (Ao et al., 2024) ✘ 4 ✘ ✘ ✔ ✘ Paralinguistic OpenAudioBench (en) (Li et al., 2025) ✘ 2 ✔ ✘ ✔ ✘ Knowledge, Single Round SpeechInstructBench (Wang et al., 2025a) ✘ 1 ✘ ✘ ✔ ✘ Instruction Following V oiceBench (Chen et al., 2024b) ✘ 8 ✔...
https://arxiv.org/abs/2505.15727v1
the optimal result in each subgroup. The numbers below each source denote the entries contained. D.3 Reasoning S2t and S2s Results The Qwen2.5-max evaluation performance of both s2t and s2s form on the math subset and the reason- ing set is shown in Table 6. The bold shows that compared with text responses, the semanti...
https://arxiv.org/abs/2505.15727v1
Emotion Probability Paralinguistic Mini-Omni It sounds like you’re feeling frustrated and thoughtfully heard. It’s important to remember that you’re feeling there. It’s important to communicate with him to express your feelings and feelings. It’s important to remember that everyone is positive and deserves to be apprec...
https://arxiv.org/abs/2505.15727v1
they handle themselves in social situations. People often draw attention to those they find impressive or charismatic.Regarding congratulating him on his accomplishmentsachievements,it’s important to acknowledge and celebrate others’ successes.Here are a few suggestions on how to handle the situation: 1. CongBe genuine...
https://arxiv.org/abs/2505.15727v1
is responsible for producing proteins in a cell? Ribosome Celebrity 193 Who won the first season of Survivor? Richard Hatch Chemistry 176 Chemical reactions involve a transfer of heat energy. This is measured in what? joules Economics 81 What was the name of the first independent credit payment card, inspired in 1949 b...
https://arxiv.org/abs/2505.15727v1
relationship, we find that subtracting ten from twice Jerry’s age gives his current age. Simplifying further, we determine that Jerry’s age is ten. To find out how old Jerry will be in three years, add three to his current age of ten, which results in thirteen. So the answer is 13. Story 100 A sick stag lay down in a q...
https://arxiv.org/abs/2505.15727v1
golden path across the shimmering ocean. Waves crash against the rugged cliffs below, their rhythmic roar harmonizing with the cool breeze. The salty tang of the sea fills the air, while shadows stretch long over the rocky edge. Standing there, amidst nature’s grandeur, evokes a sense of awe and serenity, as if time st...
https://arxiv.org/abs/2505.15727v1
B and B is taller than C. Who is the tallest currently?", "assistant": "Based on the given information, A is the tallest among the three people.", "user": "Now there are two more people, D and E. D is higher than B and E is higher than D. Who is the tallest at the moment?", "assistant": "Based on the additional informa...
https://arxiv.org/abs/2505.15727v1
that answer in simpler terms?Sure, living healthily means eating well, staying active, getting enough sleep, dealing with stress, not smoking or drinking too much, staying positive, and seeing your doctor regularly. Math Reasoning20 ["user": "If Jim has 3 hats, 5 shirts, and 4 pairs of pants, and he wears a shirt with ...
https://arxiv.org/abs/2505.15727v1
even hide serious illnesses. Always consult your doc first. Stay safe, not sorry!", "user": "If you were to explain the risks of self-medicating with antibiotics to children, how would you simplify the message?", "assistant": "To explain it to kids, I’d say: Hey kids, taking medicine like antibiotics without checking w...
https://arxiv.org/abs/2505.15727v1
a good starting point. Have you also considered any debts you would want covered by the insurance?"]I have a mortgage that I would want to be paid off.That’s an important factor. It might be helpful to talk to a financial advisor to calculate the necessary coverage based on your debt, income, and dependents’ needs. Sel...
https://arxiv.org/abs/2505.15727v1
& emotion50 Repeat a question with emotion at specific speed.Repeat the following question in surprised emotion at half my speaking speed. I just got a promotion at work and I can’t believe it! How did this happen so suddenly? Num 50 Answer a question with specefic number of points.What are the best exercises for begin...
https://arxiv.org/abs/2505.15727v1
to explain that I’ve been dealing with unexpected personal issues. I am not sure about the format, so I will write whatever you say. Table 17: Evaluation samples in instruction following set. 23 G Qwen2.5-max Prompt for Evaluation Figure 5: Evaluation prompt for reasoning set. Figure 6: Evaluation prompt for the safety...
https://arxiv.org/abs/2505.15727v1
arXiv:2505.15734v1 [cs.CL] 21 May 2025DEBATE , TRAIN , EVOLVE : Self-Evolution of Language Model Reasoning Gaurav Srivastava1, Zhenyu Bi1, Meng Lu1, Xuan Wang1 1Department of Computer Science, Virginia Tech, Blacksburg, V A, USA, (gks, zhenyub, menglu, xuanw)@vt.edu Abstract Large language models (LLMs) have improved s...
https://arxiv.org/abs/2505.15734v1
with efficient single-model inference. Specifically, we introduce a ground-truth-free training approach in which a model learns from its own debate traces generated during MAD, thereby evolving autonomously over iterative training cycles. Our framework addresses key challenges of existing methods by extracting high-qua...
https://arxiv.org/abs/2505.15734v1
incorporate explicit reinforcement learning into the debate pro- cess. For example, the ACC-Collab framework (Estornell et al., 2024) utilized an actor-critic ap- proach to explicitly optimize agent collaboration, yielding superior performance on reasoning tasks. Self-Evolution in Language Models SELF -INSTRUCT (Wang e...
https://arxiv.org/abs/2505.15734v1
a three -agent Qwen -1.5B committee, sycophancy reached 0.28 (28% of the debates have sycophancy rounds). These effects lead to a substantial fraction of [cor- rect→incorrect] transitions during debate. 3.1 R EFLECT –CRITIQUE –REFINE Prompting Inspired by previous works that had iterative self-feedback procedures (Mada...
https://arxiv.org/abs/2505.15734v1
a query xand a student output ywe define the shaped reward r(x, y) =wvote[y=y⋆] +wfmtisFmt( y) +wbrevexp(−|y|/τ), where [·]is the indicator function, isFmt checks the<reasoning> <answer> XML template, and |y|is the token length. Weights are set to (wvote, wfmt, wbrev) = (2 ,0.5,0.5)andτ= 120 . GRPO maximises the clippe...
https://arxiv.org/abs/2505.15734v1
agents. For evolution we adopt LoRA fine-tuning (rank 128, dropout 0.05) on attention and MLP pro- jections, freezing embeddings and layer norms. GRPO is optimized with AdamW (learning rate 2×10−5, weight decay 0.01, 50-step linear warm- up). Each evolution epoch processes 8k debate traces ( ∼2 M tokens) and runs on A1...
https://arxiv.org/abs/2505.15734v1
rather than memorising dataset-specific patterns. 5 ModelFine-tuned on GSM8K Fine-tuned on GSM-Plus GSM-Plus ARC-Easy ARC-Challenge CommonsenseQA GSM8K ARC-Easy ARC-Challenge CommonsenseQA (∆) ( ∆) ( ∆) ( ∆) ( ∆) ( ∆) ( ∆) ( ∆) Qwen-2.5-1.5B +9.21 ↑ -1.60↓ +0.67↑ -2.23↓ +10.32 ↑ -1.52↓ +0.24↑ -2.31↓ Qwen-2.5-3B +3.79 ↑...
https://arxiv.org/abs/2505.15734v1
new reasoning step. These observations confirm that RCR is a neces- sary pre-step for producing high-quality traces later utilized by the DTE training loop. 2) H OW MANY AGENTS ARE ENOUGH ?Re- sults shows that three agents MAD captures 85- 95 % of the maximum gains. Figure 4 sweeps the agents size from 1−7and reports t...
https://arxiv.org/abs/2505.15734v1