text string | source string |
|---|---|
2.58 0.9735 -100 % MCTS – – – – – 2.49 0.9735 DialogXpert (Vicuna 13B) 2.93 0.9415 0.3811 2.70 0.9651 2.24 0.9883 DialogXpert (Qwen 2.5 14B) 2.32 0.9746 0.4389 2.31 0.9876 2.03 0.9951 Table 4: Ablation of the top- kaction candidates in Di- alogXpert, showing average turns (AT ↓), success rate (SR↑) and satisfaction lev... | https://arxiv.org/abs/2505.17795v1 |
span an open-ended space. While useful for nuanced responses, this places additional load on the LLM. Using a lightweight emotion clas- sifier or a predefined set of emotion labels could simplify learning and improve consistency. The CIMA dataset, focused on English–Italian translation, may not be ideal for tutoring ta... | https://arxiv.org/abs/2505.17795v1 |
Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers), ACL 2023 , pages 4079–4095. Jacob Devlin. 2018. Bert: Pre-training of deep bidi- rectional transformers for language understanding. arXiv preprint arXiv:1810.04805 . Yao Fu, Hao Peng, Tushar Khot, and Mirella Lapata. 2023. Improving lan... | https://arxiv.org/abs/2505.17795v1 |
Wieland Eck- ert. 1997. Learning dialogue strategies within the markov decision process framework. In 1997 IEEE Workshop on Automatic Speech Recognition and Un- derstanding Proceedings , pages 72–79. IEEE. Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, and Minlie Huang. 2021. Towar... | https://arxiv.org/abs/2505.17795v1 |
Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. ArXiv , abs/2302.13971. Dirk Väth, Lindsey Vanderlyn, and Ngoc Thang Vu. 2023. Conversational tree search: A new hybrid dialog task. arXiv preprint arXiv:2303.10227 . Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Aja... | https://arxiv.org/abs/2505.17795v1 |
2020. Learning goal-oriented dialogue policy with opposite agent awareness. ArXiv , abs/2004.09731. Stephen Zhao, Rob Brekelmans, Alireza Makhzani, and Roger Grosse. 2024. Probabilistic inference in lan- guage models via twisted sequential monte carlo. arXiv preprint arXiv:2404.17546 . Weixiang Zhao, Yanyan Zhao, Xin L... | https://arxiv.org/abs/2505.17795v1 |
provided. Your task is to decide the most therapeutically helpful next action the therapist should do based on the patient’s emotion history and the conversation flow. The therapist’s goal is to help the patient feel emotionally understood, supported, and to make progress toward emotional resolution Conversation Histor... | https://arxiv.org/abs/2505.17795v1 |
hints for correct translation? 2.Identification : Which assistant better spots the student’s translation errors? 3.Overall : Which assistant teaches more effectively? All three selections are required before moving on. Responses are auto-saved; log back in with the same User ID to resume. B.2 Results: CIMA On the CIMA ... | https://arxiv.org/abs/2505.17795v1 |
sample, two LLMs are prompted as the user and assistant to mimic dynamic user-assistant interaction. Both the roles and instructions of the respective LLMs are delivered to their respective LLM (more in Ap- pendix F). During the assistant’s turn, the policyLLM will predict the top- kactions that are recom- mended and t... | https://arxiv.org/abs/2505.17795v1 |
playing as the buyer in the conversation, the goal is to buy a given product as close as pos- sible to the buyer’s target price in order to maximize profit. •ExTES : Emotional support and therapy. Sim- ilar to ESConv but more diverse and larger in sample size. The goal, as a therapist, is to help the patient resolve th... | https://arxiv.org/abs/2505.17795v1 |
fulfillment. The prompts for the critic LLM is in the text boxes with the title of "Critic LLM for {dataset}". F.5 Strategy Prompting Here, we present the mapping of dialogue strategies to their corresponding natural language prompts, utilized as [action] to direct the actions undertaken by the dialogue system. The ful... | https://arxiv.org/abs/2505.17795v1 |
flow. The goal is to maximize the buyer’s benefit. Directive Conversation so far :[full_conversation ] Emotion History: [user _emotions ] Options: [options ] Choose the TOP 4 most suitable actions from the given options list. Reply ONLY in the given format: 1,2,4,5 Policy LLM for ESConv Instruction You are a specialist... | https://arxiv.org/abs/2505.17795v1 |
[therparist _last_utterance ]. Express how you feel in a natural, emotional way. Please reply with only one short and succinct sentence. User LLM for P4G Instruction You are role playing as a persuadee in a persuasive conversation. A persuader is trying to convince you to donate to a charity called ’Save the Children’ ... | https://arxiv.org/abs/2505.17795v1 |
based on that emotional state, respond as the persuader using ONE short and persuasive sentence (Response: ...). [action _prompt ] Critic LLM for ExTES Instruction You are an expert in assessing counseling sessions between a patient and a therapist. Your task is to evaluate whether the conversation helped improve the p... | https://arxiv.org/abs/2505.17795v1 |
Children’. The persuadee’s emotional states throughout the conversation were: [emotion _states ] Directive Conversation so far :[full_conversation ] Please evaluate the following conversation and strictly choose ONE of the exact responses listed below. Question: Has the persuadee has been successfully convinced to make... | https://arxiv.org/abs/2505.17795v1 |
way without making any judgments. Suggest Options Please suggest possible options or actions the user could consider. Collaborative Planning Please invite the user to collaboratively make a plan or decision together. Provide Different Perspectives Please help the user consider a different point of view or alternative w... | https://arxiv.org/abs/2505.17795v1 |
got any support from the government. Therapist : It sounds like you’re feeling anxious and uncertain about your job security due to the current financial situation. Patient : Yes, I am feeling extremely anxious and uncertain about my job and financial stability. Therapist : I understand that this situation is causing y... | https://arxiv.org/abs/2505.17795v1 |
let my fear of job loss consume my thoughts and affect my daily life. Therapist : I hear you, and it’s important to acknowledge those fears. Patient : Thank you for understanding. I just need some guidance on how to manage this fear and find some peace of mind. Patient : That sounds helpful. How can I start practicing ... | https://arxiv.org/abs/2505.17795v1 |
a constant source of anxiety for me. I feel like I’m constantly on edge, waiting for the other shoe to drop. Therapist : It’s completely understandable that you would feel on edge and anxious given the uncertainty surrounding your job situation. It’s important to acknowledge and address these feelings. Patient : I just... | https://arxiv.org/abs/2505.17795v1 |
place to start. What self-care strategies do you recommend for managing anxiety in the face of job uncertainty? Therapist : Some self-care strategies that may help manage anxiety during job uncertainty include maintaining a routine, practicing relaxation techniques such as deep breathing or meditation, engaging in phys... | https://arxiv.org/abs/2505.17795v1 |
arXiv:2505.17813v1 [cs.CL] 23 May 2025Don’t Overthink it . Preferring Shorter Thinking Chains for Improved LLM Reasoning Michael Hassid1,2, Gabriel Synnaeve1, Yossi Adi1,2, Roy Schwartz2 1FAIR Team, Meta2The Hebrew University of Jerusalem Abstract Reasoning large language models (LLMs) heavily rely on scaling test-time... | https://arxiv.org/abs/2505.17813v1 |
answer is 49majority@k Final answer: 52 <think> ………………. // Terminated thinking <think> ………………. // Terminated thinking <think> ………………. // Terminated thinking <think> ………………. </think> So the answer is 49 Final answer: 49 short-1@k (ours) Figure 1: Visual comparison between majority voting and our proposed method short-m@... | https://arxiv.org/abs/2505.17813v1 |
Anthropic, 2025, Bercovich et al., 2025, Guo et al., 2025, sky, 2025, DeepMind, 2025, Team, 2025b]. This capability is fundamentally based on techniques like 2 chain-of-thought [CoT; Wei et al., 2022], which encourages models to generate intermediate reasoning steps before arriving at a final answer. By using a greater... | https://arxiv.org/abs/2505.17813v1 |
Moreover, our proposed inference method short-m@k is designed to enhance the efficiency of reasoning LLMs by leveraging this property. 3 Shorter thinking is preferable As mentioned above, the common wisdom in reasoning LLMs suggests that increased test-time computation enhances model performance. Specifically, it is wi... | https://arxiv.org/abs/2505.17813v1 |
We compare short vs.long thinking chains for the same question, along with a random chain. Results are presented in Table 2. First, as expected, the shortest answers are 25%–50% shorter compared to randomly sampled responses. However, we also note that across almost all models and benchmarks, considering the answer wit... | https://arxiv.org/abs/2505.17813v1 |
soon as the m≤kshortest thinking trajectories are completed. It then conducts majority voting among those shortest answers, resolving ties by selecting the answer with the shortest thinking chain. Given that thinking trajectories can be computationally intensive, terminating all generations once the mshortest trajector... | https://arxiv.org/abs/2505.17813v1 |
our method ( short-m@k ), we terminate all other generations after the first mdecoding thinking processes terminate. Thus, the overall thinking compute is the total number of thinking tokens for each of the kgenerations at that point. Similarly, the overall time is that of the m’th shortest generation process. Converse... | https://arxiv.org/abs/2505.17813v1 |
compute budgets of 45k and 60k total thinking tokens, respectively, but is underperformed by it on larger compute budgets. The short-3@k method yields even greater performance improvements, incurring only a modest increase in thinking compute compared to short-1@k . When compared to majority @k,short-3@k consistently a... | https://arxiv.org/abs/2505.17813v1 |
reasoning chain among the vote-leading options. We compare this strategy to random tie-breaking, and to tie breaking according to the longest reasoning chain among the options. As shown in Figure 5b, theshort-m@k strategy outperforms random tie-breaking. In contrast, choosing the option with the longest reasoning chain... | https://arxiv.org/abs/2505.17813v1 |
sequences can lead to models that not only exhibit reduced computational overhead but also enhanced performance. This observation aligns with our findings in Section 3, which shows that answers with shorter thinking trajectories tend to be more accurate. We believe that developing models that reason more effectively wi... | https://arxiv.org/abs/2505.17813v1 |
Chowdh- ery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 , 2022. Marah Abdin, Sahaj Agarwal, Ahmed Awadallah, Vidhisha Balachandran, Harkirat Behl, Lingjiao Chen, Gustavo de Rosa, Suriya Gunasekar, Mojan Javaheripi, Neel Joshi, et al. Phi-4-re... | https://arxiv.org/abs/2505.17813v1 |
. Mislav Balunovi ´c, Jasper Dekoninck, Ivo Petrov, Nikola Jovanovi ´c, and Martin Vechev. Math- arena: Evaluating llms on uncontaminated math competitions, February 2025. URL https: //matharena.ai/ . Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Sto... | https://arxiv.org/abs/2505.17813v1 |
2025 - thinking compute comparison. 13 8 10 12 14 16 18 Time-to-Answer (longest thinking in thousands)0.5750.6000.6250.6500.6750.7000.7250.7500.775Accuracy k=1 k=3 k=5 k=9 k=1 k=3 k=5 k=9 k=1 k=3 k=5 k=9(a) LN-Super- 49B 6 8 10 12 14 16 Time-to-Answer (longest thinking in thousands)0.720.740.760.780.800.820.84Accuracy ... | https://arxiv.org/abs/2505.17813v1 |
arXiv:2505.17816v1 [cs.CL] 23 May 2025Low-Resource NMT: ACase Studyon the Wri/t_tenand Spoken Languages in HongKong HeiYi Mak TheChinese University ofHongKong HongKongTan Lee TheChinese University of HongKong HongKong ABSTRACT The majority of inhabitants in Hong Kong are able to read and writeinstandardChinesebutuseCan... | https://arxiv.org/abs/2505.17816v1 |
red lan- guage. Nevertheless, writinginCantonese has becomevery p opu- lar among internet and mobile users. With the prevalence of i n- stant messaging and social media, as well as millions of nati ve speakersaroundtheglobe,writtenCantonesehasfounditsi mpor- tanceand usage inonline social communication.For simplic ityo... | https://arxiv.org/abs/2505.17816v1 |
Cantonese畀杯水我(“give” “cup”“water” “me”) Example2 English Iam tallerthanyou. Chinese我比你高(“I” “compare” “to”“you” “tall”) Cantonese我高過你(“I” “tall”“than” “you”) Example3 English Eatmore. Chinese多吃點(“more” “eat” “some”) Cantonese食多o的(“eat” “more” “some”) 3 LINGUISTIC CONSIDERATIONS IN CHINESE-TO-CANTONESE TRANSLATION 3.1 L... | https://arxiv.org/abs/2505.17816v1 |
tween Chinese and Cantonese both require great efforts. In th is study,paralleldataare collectedfrom previous linguisti c research and the internet. The largest dataset we were able to locate c on- tains barely more than 10K parallel sentences. Combining al l the datasets we found, there are around 28K sentence pairs. T... | https://arxiv.org/abs/2505.17816v1 |
data for training NMT sys- tems. Among versions of Wikipedia in different Chinese diale cts, thestandardChinese(zh)WikipediaandCantonese(zh-yue) Wikipedia are the most prominent versions with around 1.1M articles an d around100Karticlesrespectively.Weexplorethepossibil ityofex- tractingparallelsentences from thesetwover... | https://arxiv.org/abs/2505.17816v1 |
Eac h of the 7 other non-wiki datasets is split into training, valida tion and testsetsintheproportion8:1:1.Thedatapartitionarrang ement is detailed as shown in Table 2. A non-wiki validation set is for med bymergingthe7validationsetswiththewikivalidationset being excluded.The8test sets areusedseparately forevaluation ... | https://arxiv.org/abs/2505.17816v1 |
“開o.t.” or “開OT”. This is indeed a common practice of code- switchingin Cantonese. In these examples, our system demonstrates the ability to pe r- form appropriate lexical transformation and code-switchi ng, and superiorperformancein wordreordering. 9 CONCLUSION Lacking parallel data resources is the major challenge in... | https://arxiv.org/abs/2505.17816v1 |
2017. Quantita- tive comparative syntax on the Cantonese-Mandarin paralle l dependency tree- bank. InProceedings of the Fourth International Conference on Depen dency Lin- guistics(Depling 2017) .266–275. [15] Tak-sum Wong and John SY Lee. 2018. Register-Sensitive Translation: A Case Study of Mandarin and Cantonese (No... | https://arxiv.org/abs/2505.17816v1 |
PATIENT SIM: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions Daeun Kyung1, Hyunseung Chung1, Seongsu Bae1, Jiho Kim1, Jae Ho Sohn2,Taerim Kim3,Soo Kyung Kim4,∗,Edward Choi1,∗ 1KAIST2UCSF3Samsung Medical Center4Ewha Womans University {kyungdaeun,edwardchoi}@kaist.ac.kr1,sookim@ewha.ac.kr4 Abstract D... | https://arxiv.org/abs/2505.17818v1 |
and your symptoms can indeed suggest an infection. Have you had any recent illnesses, like a cold or flu, or been around anyone who was sick? Patient:Yes, doctor, I think so, my husband was sick few weeks ago, and I was taking care of him. I didn't feel good then, but I thought it was just stress, now I'm worried I cau... | https://arxiv.org/abs/2505.17818v1 |
170 profiles (Sec. 4). For personas, we defined 37 distinct combinations across four axes, designed to reflect key factors impacting doctor-patient consultation quality, based on literature reviews and guided by medical experts (Sec. 5.1). We evaluate eight LLMs as the backbone of our simulator and select Llama 3.3 as ... | https://arxiv.org/abs/2505.17818v1 |
and relational nuances, making them unsuitable for simulating patients in general diagnostic consultation settings such as hospital emergency departments. Unlike previous works, our study proposes a realistic patient simulator that combines the emotional realism emphasized in psychological counseling with the clinical ... | https://arxiv.org/abs/2505.17818v1 |
items, covering demographics, social and medical history, and ED visit details (see Appendix A.3). Clinical experts reviewed each item for relevance. Target disease selection We select the five prevalent diseases from the MIMIC-IV-ED dataset: my- ocardial infarction, pneumonia, urinary tract infection, intestinal obstr... | https://arxiv.org/abs/2505.17818v1 |
a process of LLM evaluation, 4 qualitative analysis by the authors, and two rounds of feedback from medical experts. In the first round, two medical experts, who are also co-authors, provided feedback after engaging in extensive conversations with our simulators. The second round incorporated input from four additional... | https://arxiv.org/abs/2505.17818v1 |
t=1, where ui tis the utterance at turn t. Each utterance ui t may contain multiple sentences, denoted as ui t={si tm}M m=1, where Mis the number of sentences in utterance ui t. We classify si tmassupported if it is related to at least one profile item xi k, and unsupported if it is unrelated to any profile items. Sent... | https://arxiv.org/abs/2505.17818v1 |
item, as the sentence si tmis deemed unrelated to xi k. The final factual accuracy of the sentence si tmis represented by Entail (%), calculated as follows, Entail (Di) =PT t=1PM m=11[C(si tm) =info]·max k ri k·1[NLI (si tm, xi k) =entail ] PT t=1PM m=11[C(si tm) =info](2) which reflects the percentage of supported s... | https://arxiv.org/abs/2505.17818v1 |
any unsupported sentences), thus limiting the flow of doctor-patient dialogue, we instead let PATIENT SIManswer such questions based on the given profile ( i.e., allowing unsupported sentences). However, it is essential to assess the clinical plausibility of those unsupported sentences, in order to guarantee the overal... | https://arxiv.org/abs/2505.17818v1 |
Appendix F.4. For human evaluation, we recruited four general practitioners2through Ingedata3, an AI data annotation company. Detailed information is provided in Appendix E. 7 Results In this section, we report the performance of various LLMs with respect to RQ1, 2 , and 3, using LLM- as-judge [ 62]. Based on these eva... | https://arxiv.org/abs/2505.17818v1 |
– 0.879 (0.843, 0.913) Clinician D 0.866 (0.828, 0.901) 0.853 (0.818, 0.886) 0.879 (0.843, 0.913) – Plausibility (4 point scale) Plausibility 3.955 3.923 3.985 3.781 RQ3: Can LLMs reasonably fill in the blanks? To address this question, we focus on the unsupported sentences that include at least one piece of informatio... | https://arxiv.org/abs/2505.17818v1 |
virtual reality (VR) simulations, would allow for more comprehensive modeling of patient personas. Second, increasing the scale and diversity of human evaluators can provide more reliable validation of LLM-based assessments. 9 References [1]M. Almansoori, K. Kumar, and H. Cholakkal. Self-evolving multi-agent simulation... | https://arxiv.org/abs/2505.17818v1 |
B. Moody, C.-K. Peng, and H. E. Stanley. Physiobank, physiotoolkit, and physionet: Components of a new research resource for complex physiologic signals. Circulation [Online] , 101(23):e215–e220, 2000. doi: 10.1161/01.CIR.101.23.e215. [16] A. Grattafiori et al. The llama 3 herd of models, 2024. URL https://arxiv.org/ab... | https://arxiv.org/abs/2505.17818v1 |
collaboration of llms for medical decision-making. In The Thirty-eighth Annual Conference on Neural Information Processing Systems , 2024. [30] M. B. Laws, Y . Lee, T. Taubin, W. H. Rogers, and I. B. Wilson. Factors associated with patient recall of key information in ambulatory specialty care visits: Results of an inn... | https://arxiv.org/abs/2505.17818v1 |
In Proceedings of the Conference on Health, Inference, and Learning , pages 248–260, 2022. [45] M. C. Peterson, J. H. Holbrook, D. V on Hales, N. L. Smith, and L. V . Staker. Contributions of the history, physical examination, and laboratory investigation in making medical diagnoses. Western Journal of Medicine , 156(2... | https://arxiv.org/abs/2505.17818v1 |
Corrado, Y . Matias, A. Karthikesalingam, and V . Natarajan. Towards conversational diagnostic ai, 2024. URL https://arxiv.org/abs/ 2401.05654 . [58] J. Wang, Y . Xiao, Y . Li, C. Song, C. Xu, C. Tan, and W. Li. Towards a client-centered assessment of llm therapists by client simulation, 2024. URL https://arxiv.org/abs... | https://arxiv.org/abs/2505.17818v1 |
. 21 B.2 Language proficiency . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 B.3 Medical history recall level . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 B.4 Cognitive confusion level . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 C Simulation of doctor-patient... | https://arxiv.org/abs/2505.17818v1 |
. . 36 F.2 RQ2: Do LLMs accurately derive responses based on the given profile? . . . . . . 38 F.3 RQ3: Can LLMs reasonably fill in the blanks? . . . . . . . . . . . . . . . . . . . . 39 F.4 Ablation study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 F.4.1 Validation of sentence-level cl... | https://arxiv.org/abs/2505.17818v1 |
0–10 range were treated as outliers and removed. • We cap the maximum number of medication per patients at 15. •The History of Present Illness (HPI) section was limited to a maximum of 350 words and a minimum of 10 words. The Past Medical History (PMH) section was limited to a maximum of 80 words. •To ensure the accura... | https://arxiv.org/abs/2505.17818v1 |
item is summarized in Table A1. For simplicity, we use shortened dataset paths, like mimic-iv-ed/edstays instead of mimic-iv-ed/2.2/ed/edstays . Disposition and diagnosis are not shared with the doctor but are included to enhance the simulator’s understanding of the patient’s status and condition severity during role-p... | https://arxiv.org/abs/2505.17818v1 |
24 (14.1%), Asian - Chinese: 6 (3.5%), Black/Cape Verdean: 6 (3.5%), Hispanic/Latino - Puerto Rican: 6 (3.5%), Other: 5 (2.9%), Asian: 2 (1.2%), Asian - Asian Indian: 2 (1.2%), Hispanic/Latino - Dominican: 2 (1.2%), White - Other European: 2 (1.2%), White - Russian: 2 (1.2%), Asian - South East Asian: 1 (0.6%), Black/A... | https://arxiv.org/abs/2505.17818v1 |
unnecessary words. 4.If a field contains multiple values, combine them into a single string separated by semi- colons. 5.Treat de-identified placeholders as nonexistent. Do not include placeholders like ‘___’ in any of output fields. 6. Return ‘Not recorded’ for any field not mentioned in the EHR. Figure A2: System pro... | https://arxiv.org/abs/2505.17818v1 |
frequency, and amount. –illicit_drug: Use of non-prescribed or illegal substances, including type, amount, and fre- quency. – sexual_history: Sexual activity, including partner(s), protection use, frequency, and timing. Guidelines: 1.For any field marked as ‘Not recorded’, generate a realistic and plausible entry that ... | https://arxiv.org/abs/2505.17818v1 |
overall proficiency level. B.3 Medical history recall level We define medical history recall at two levels: high and low. Detailed descriptions of each level are provided in Table B5. Table B3: Prompts for personality types used in P ATIENT SIM Persona Type Description Neutral 1. Provide concise, direct answers focused... | https://arxiv.org/abs/2505.17818v1 |
to be explained in very simple, everyday language. Below are examples of words within and beyond your level. You cannot understand words more complex than the examples provided within your level. Words within your level: {understand_med_words}. Words beyond your level: {misunderstand_med_words}. IMPORTANT: If a questio... | https://arxiv.org/abs/2505.17818v1 |
Dazedness (Initial Phase) –Repeatedly provide highly unrelated responses. –Overly fixate on a specific discomfort or pain, and keep giving the same information regardless of the question. For example, when asked ’Are you short of breath?’, fixate on another issue by saying, ’It hurts so much in my chest,’ without addre... | https://arxiv.org/abs/2505.17818v1 |
gender, age, and arrival transport), which are typically known to clinicians prior to initiating history taking to help their clinical reasoning and questioning strategy. 23 Prompt template for P ATIENT SIM Imagine you are a patient experiencing physical or emotional health challenges. You’ve been brought to the Emerge... | https://arxiv.org/abs/2505.17818v1 |
acts without confusion. high at first, you should act like a highly dazed and extremely confused patient who cannot understand the question and gives highly unre- lated responses. Gradually reduce your dazed state throughout the conversation, but only with reassurance from the doctor. General behavioral guideline for P... | https://arxiv.org/abs/2505.17818v1 |
enough information or if the patient declines further discussion, provide the top {top_k_diagnosis} differential diagnoses based on the information collected so far. Use the following format: “[DDX] (list of differential diagnoses)” The patient’s basic information is as follows: • gender: {gender} • age: {age} • ED arr... | https://arxiv.org/abs/2505.17818v1 |
their assigned recall level ( e.g., low or high). • The patient’s coherence and clarity of thought match the assigned level of cognitive confusion. • The patient’s overall communication style matched what I would expect from a real ED patient. Each simulated patient is assigned four distinct persona axes: personality, ... | https://arxiv.org/abs/2505.17818v1 |
information ( C(si tm)). This step follows the prompt defined in Figure D10. 2.Identify the related profile items : For each sentence si tmclassified as information, we identify which of the patient’s profile items xi kit relates to. The output is a binary vector R(si tm) = [ri 1, ri 2, . . . , ri K], where ri k= 1ifsi... | https://arxiv.org/abs/2505.17818v1 |
categories (apply the same format to all categories): [ { "category": "age", "explanation": "The utterance ‘I am 45 years old’ mentions the patient’s age.", "prediction": 1 }, { "category": "gender", "explanation": "The utterance does not mention the patient’s gender.", "prediction": 0 } ] Figure D11: System prompt tem... | https://arxiv.org/abs/2505.17818v1 |
the pain field, if patients do not explicitly state a score, predict the score (0–10) based on their description and note it as predicted ( e.g., ‘3 (predicted)’). 7. Maintain the exact JSON structure without adding or removing fields. [User Prompt ] Conversation: {conversation} Figure D13: Prompt template for extracti... | https://arxiv.org/abs/2505.17818v1 |
implied, are consid- ered new. For example, if the profile lists ‘aspirin’ and ‘heart failure’ separately, stating ‘aspirin for heart failure’ is new. Similarly, if only medication names are listed without frequency, stating ‘I take aspirin daily’ is new. 4.For allergies, family history, medical devices, and medication... | https://arxiv.org/abs/2505.17818v1 |
consultations (see Figure E17 for screenshots). In response to clinician feedback, we added a Review of Systems checkboxes12to mirror real-world clinical workflows. Consultation logs, diagnoses, and survey responses were stored in Google Sheets for easy access and analysis. Each virtual patient had a unique clinical pr... | https://arxiv.org/abs/2505.17818v1 |
is prompted to provide its top five differential diagnoses. This prediction is considered correct if the ground-truth diagnosis appeared in this list. To ensure consistent evaluation despite free-text outputs, we use the prompt shown in Figure F19. On average, the doctor LLM completed the consultation and provided a fi... | https://arxiv.org/abs/2505.17818v1 |
Y or N only, without further explanation. Predicted differential diagnoses: {ddx} True diagnosis: {ans} Answer [Y/N]: Figure F19: Prompt template for evaluating differential diagnosis accuracy. F.1.2 Additional result of human evaluation For human evaluation, clinicians conducted consultations in total of 108 virtual p... | https://arxiv.org/abs/2505.17818v1 |
And yes, I've lost my appetite, food doesn't taste good to me anymore. (…) I'm worried that I might choke on my food again. My appetite has been bad for a while, but it's gotten worse in the past two days.Doctor :Did you have trouble breathing for the past two days? Do you also have loss of appetite?Patient :No fever, ... | https://arxiv.org/abs/2505.17818v1 |
iterations. Metric Gwet AC 1(95% CI) Gwet AC 2(95% CI) Personality 0.897 (0.830, 0.949) 0.957 (0.919, 0.987) Language proficiency 0.347 (0.218, 0.471) 0.818 (0.745, 0.876) Medical history recall level 0.693 (0.585, 0.786) 0.916 (0.865, 0.957) Cognitive confusion level 1.000 (1.000, 1.000) 1.000 (1.000, 1.000) Realism 0... | https://arxiv.org/abs/2505.17818v1 |
70B generated the fewest contradictory responses, leading us to select it as our final model. To better understand these contradiction errors, we analyzed them in detail in Table F13. The most common contradictions occurred when a patient’s pain level was recorded as zero. This often happened when pain was the reason f... | https://arxiv.org/abs/2505.17818v1 |
0.960) 0.945 (0.926, 0.961) 0.964 (0.947, 0.977) 0.883 (0.857, 0.907) F.4 Ablation study F.4.1 Validation of sentence-level classification We validated the performance of an LLM sentence classifier in detecting supported and unsupported statements using 10 distinct profiles. From 10 consultations, we extracted 411 sent... | https://arxiv.org/abs/2505.17818v1 |
amount and consistency of information extracted. These metrics were calculated for 108 patients, each assigned one of 37 distinct personas randomly. In this study, we varied only the doctor model, testing Gemini-2.5-flash, Gpt-4o-mini, and Llama 3.3 70B, while fixing the PATIENT SIMLLM backbone to Llama 3.3 70B. In Tab... | https://arxiv.org/abs/2505.17818v1 |
Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models Xuchen Pan∗†, Yanxi Chen∗†, Yushuo Chen∗, Yuchang Sun∗, Daoyuan Chen∗, Wenhao Zhang, Yuexiang Xie, Yilun Huang, Yilei Zhang, Dawei Gao, Yaliang Li†, Bolin Ding†, Jingren Zhou Alibaba Group Trinity-RFT is a genera... | https://arxiv.org/abs/2505.17826v1 |
complex agent- environment interaction. •Systematic data pipelines optimized for RFT. These include converting raw datasets to task sets for RFT, cleaning/filtering/prioritizing experiences stored in the buffer, incorporating priors and additional reward signals from various sources into the collected experiences, synt... | https://arxiv.org/abs/2505.17826v1 |
useful for experimental purposes; for example, the user might want to try out different RFT techniques or configurations quickly (with limited evaluation on hold-out data) during training, identify which RFT trials have achieved stable convergence and high rewards, and then conduct more thorough evaluations only for th... | https://arxiv.org/abs/2505.17826v1 |
for asynchronous RFT modes , which allow great flexi- bility in the paces of the explorer and trainer. This can boost the overall efficiency of the RFT process, compared to synchronous modes where the slower one among the explorer and trainer can block the progress of the other and cause waste of computational resource... | https://arxiv.org/abs/2505.17826v1 |
and reward throughout the RFT process. •Trinity-RFT provides the Processor Module to support convenient and extensive data processing capabilities tailored to RFT, through dedicated bridge classes that link Trinity-RFT to over 100 operators from the Data-Juicer system [2]. This module offers efficient integration with ... | https://arxiv.org/abs/2505.17826v1 |
We thus prioritize flexibility in both the interaction-interface and service levels. Examples include rich built-in interfaces that can be extended in a visualized style with XML-like tags provided by Label Studio, fine-grained quality scoring for reward shaping, free-form feedback attachment for dataset shaping, among... | https://arxiv.org/abs/2505.17826v1 |
LLM, both compatible with HuggingFace [9] and ModelScope [13] formats. Listing 1 gives a minimal example for implementing a single-turn workflow. Suppose that each task is specified by a <question, answer> tuple. The run()method of ExampleWorkflow calls the LLM once to generate a response for the question, calculates i... | https://arxiv.org/abs/2505.17826v1 |
34 def run(self) -> List[Experience]: 35 # ... 36 game_file_path = self.task_desc 37 rollout_n = self.repeat_times 38 # ... 39 env = create_environment(game_file_path) 40 return self.generate_env_inference_samples(env, rollout_n) Listing 2: An implementation of a multi-turn workflow for ALFWorld [25]. 4.3 Dataset Curat... | https://arxiv.org/abs/2505.17826v1 |
datasets and online instruction tuning scenarios where human judgment remains irreplaceable for quality-critical decisions, particularly in human-centric sociocultural contexts where data quality, difficulty, and reward signals are difficult to verify logically. 1# Human annotation configuration 2class HumanAnnotationC... | https://arxiv.org/abs/2505.17826v1 |
CLI procedures. We implement Trinity-Studio with Singe-Spa framework [27]. The modular architecture enables custom view development through JavaScript plugins and flexible extensions for general-purpose usage. 5 Conclusion This report has provided an overview of Trinity-RFT , a general-purpose, flexible, scalable and u... | https://arxiv.org/abs/2505.17826v1 |
Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, YuxiangLuo, YuxiangY... | https://arxiv.org/abs/2505.17826v1 |
Manning, Stefano Ermon, and Chelsea Finn. Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16 , 2023. [21] Pierre Har... | https://arxiv.org/abs/2505.17826v1 |
agent. In The Thirteenth International Conference on Learning Representations , 2025. [34] Tianbing Xu. Training large language models to reason via EM policy gradient. arXiv, 2025. [35] Zhe Xu, Daoyuan Chen, Zhenqing Ling, Yaliang Li, and Ying Shen. Mindgym: What matters in question synthesis for thinking-centric fine... | https://arxiv.org/abs/2505.17826v1 |
estimating Z=Z(x, π ref)using samples from πref(·|x). A.2 Pairwise OPMD Analysis. To eliminate the Zterm, we note that Eq. (1) is equivalent to the following: ∀y1andy2,π⋆(y1|x) π⋆(y2|x)=πref(y1|x) πref(y2|x)e r(x,y1)−r(x,y2) /τ. 17 Taking logarithm of both sides, we have logπ⋆(y1|x)−logπ⋆(y2|x) = log πref(y1|x)−logπr... | https://arxiv.org/abs/2505.17826v1 |
+β·g πθ, πsft;x, y1, . . . , y K . 19 B Additional Details for Data Pipelines B.1 Illustration of Typical Dataset Classes and Schemas The dataset shaping process described in Section 3.3 is supported by PostgreSQL persistence with compre- hensive schema designs; one example can be found in Listing 6. Key model classe... | https://arxiv.org/abs/2505.17826v1 |
arXiv:2505.17827v1 [cs.CL] 23 May 2025Not All Tokens Are What You Need In Thinking Hang Yuan1,5, Bin Yu2,5, Haotian Li2,6, Shijun Yang3,6 Christina Dan Wang4,Zhou Yu1,Xueyin Xu5,6,Weizhen Qi5,6,Kai Chen5,6, 1East China Normal University,2Harbin Institute of Technology, 3University of Science and Technology of China,4Ne... | https://arxiv.org/abs/2505.17827v1 |
token impor- tance conditioned on critical context (e.g., ques- tions and answers). As shown in Figure 1, by fil- tering CoT data at adjustable compression ratios and then fine-tuning model with compressed data, we enable models to learn how to skip unnecessary reasoning tokens during inference. We conducted extensive ... | https://arxiv.org/abs/2505.17827v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.