text string | source string |
|---|---|
a small language model to assess the importance of each lexical unit (such as sentences or tokens) in the original prompts, and then drops the less in- formative content for prompt compression. Subse- quent studies by Jiang et al. (2023, 2024) followed this line of research, proposing more fine-grained compression meth... | https://arxiv.org/abs/2505.17827v1 |
symbols are important for reaching the final answer, we curated a high-quality dataset {q, z1, . . . , z K,a}that reflects the desired data dis- tribution. Here z={z1, . . . , z K}denotes a set of concise and essential reasoning steps. We then train a RM using cross-entropy loss on the curated data. LRM=−KX i=1logP(zi|... | https://arxiv.org/abs/2505.17827v1 |
vs. Average Reasoning Tokens for CTS and TokenSkip on the Qwen2.5-7B- Instruct model across different test sets. Evaluation Benchmarks & Metrics The evalua- tion leverages three widely used reasoning bench- marks: AIME24 ,MATH500 , and GPQA Di- amond (Mathematical Association of America, 2024; Hendrycks et al., 2021; R... | https://arxiv.org/abs/2505.17827v1 |
reduced. As the compression ratio decreases, although CTS accuracy declines compared to Original, in- ference tokens continue to decrease. Thus, there exists a trade-off between accuracy and inference Table 1: Experimental results of various compression methods on Qwen2.5-14B-Instruct , showing accuracy, average reason... | https://arxiv.org/abs/2505.17827v1 |
the Qwen2.5-14B- Instruct model on the MATH500 dataset under different compression ratios Proposed method performs slightly better than the + Conditional approach, while the + RM-Tuned method shows marginal improvements over the Base method. This indicates that training the ref- erence model provides some benefit in id... | https://arxiv.org/abs/2505.17827v1 |
Value (Corresponding Ratio). Ratio Base + RM + Conditional Proposed 0.9 5023 5597 4563 5012 0.8 2510 2992 5001 4703 0.7 2511 2369 2883 3310 0.6 2270 2167 1952 3787 0.5 1998 2036 1787 2036 proposed a mixed coarse-grained and fine-grained compression method. Jiang et al. (2024) extended this work by introducing a task-aw... | https://arxiv.org/abs/2505.17827v1 |
tions, where lower compression ratios may be nec- essary to preserve interpretability. In our humble opinion, we have not discerned any potential social risks. References Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu,... | https://arxiv.org/abs/2505.17827v1 |
solu- tion: Building state-of-the-art mathematical reason- ing models with openmathreasoning dataset. arXiv preprint arXiv:2504.16891 . Niklas Muennighoff, Zitong Yang, Weijia Shi, Xi- ang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. 2025. s1: Simple... | https://arxiv.org/abs/2505.17827v1 |
how, where, and how well? Preprint , arXiv:2503.24235. Han Zhao, Haotian Wang, Yiping Peng, Sitong Zhao, Xi- aoyu Tian, Shuaiting Chen, Yunjie Ji, and Xiangang Li. 2025. 1.4 million open-source distilled reasoning dataset to empower large language model training. Preprint , arXiv:2503.19633.A Prompt Template A.1 Prompt... | https://arxiv.org/abs/2505.17827v1 |
Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning Zezhong Wang1*, Xingshan Zeng2†, Weiwen Liu3, Yufei Wang2, Liangyou Li2, Yasheng Wang2, Lifeng Shang2, Xin Jiang2, Qun Liu2, Kam-Fai Wong1 1The Chinese University of Hong Kong 2Huawei Noah’s Ark Lab,3Shanghai Jiao Tong Univers... | https://arxiv.org/abs/2505.17829v1 |
each reasoning step. Specifically, once a step is completed, we temporar- ily interrupt the reasoning process and append the prompt " So the answer is " to the current reason- ing steps, compelling the model to generate an intermediate prediction rather than continuing its reasoning process, as illustrated in the upper... | https://arxiv.org/abs/2505.17829v1 |
single search beam, DVTS oper- ates multiple search trees simultaneously, selecting and expanding the most promising reasoning path within each tree. Tree search algorithms, however, face two crucial challenges: the diversity problem and the utilization problem. The diversity problem arises when PRMs in- advertently su... | https://arxiv.org/abs/2505.17829v1 |
generation. At each checkpoint position, a fixed prompt template xckpt="So, the answer is " is inserted to force the model to generate an interme- diate prediction based solely on the accumulated context up to that step. The model’s immediate re- sponse to xckptis recorded as a checkpoint answer atat step t, after whic... | https://arxiv.org/abs/2505.17829v1 |
maximize the use of reasoning resources and enhance the diversity of candidate an- swers by integrating the checkpoint answers from intermediate reasoning steps. Traditional Beam Search methods retain only a fixed number, i.e., M, of complete reasoning paths as the final candidate set, which leads to the discard of man... | https://arxiv.org/abs/2505.17829v1 |
TTS results. The upper section shows the greedy search results for 1B and 70B models, and we additionally report the self-consistency performance of the 1B model with N= 128 . The lower section shows results from the 1B model combined with various TTS methods and two PRMs, also with N= 128 . Numbers indicate accuracy (... | https://arxiv.org/abs/2505.17829v1 |
on MATH500, SRCA achieves 51.2% accuracy at N= 16 , out- performing DVTS’s 49.8% at N= 64 . This advan- tage is more pronounced on AIME, where SRCA’s 70B 70B 70B70BFigure 2: Performance trends of TTS methods with DeepSeek PRM (top row) and Skywork PRM (bottom row) and as the sampling number Nincreases from 16 to 128. I... | https://arxiv.org/abs/2505.17829v1 |
values of N. For the bars corresponding to methods incorporating CCA, the Checkpoint Answer Rate (CAR) is additionally marked with slashes shading. The average CAR for each dataset is indicated in the top-left corner of each subplot. exceeds τ. We tested various τvalues (0.5-1.0), measuring both accuracy and average re... | https://arxiv.org/abs/2505.17829v1 |
not a perfect cube. 0.6674 $\boxed{27}$ 0.7192 ## Step 6: Now, let's try n = 2: 3(2 + 1) = 3(3) = 9, which is a perfect cube (3^2). 0.3876 $\boxed{9}$ 0.0054 ## Step 7: Since we found a perfect cube in the first step, we don't need to check further values of n. 0.0764 $\boxed{9}$ 0.1356 The final answer is: $\boxed{9}$... | https://arxiv.org/abs/2505.17829v1 |
two main limitations. First, while it requires checkpoints between reasoning steps, defining precise step boundaries is challenging. Al- though Llama-series models exhibit relatively clear step demarcations with characteristic delimiters, others, particularly the emerging "slow thinking" models, often generate outputs ... | https://arxiv.org/abs/2505.17829v1 |
the 62nd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers) , pages 3828–3850, Bangkok, Thailand. Association for Computational Linguistics. Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Zhongyuan Peng, Zhaox- iang Zhang, Zhicheng Zheng, Wenbo Su, and B... | https://arxiv.org/abs/2505.17829v1 |
Xu, and Aviral Ku- mar. 2024. Scaling llm test-time compute optimally can be more effective than scaling model parameters. Preprint , arXiv:2408.03314. Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan, Hongyi Liu, An- drew Wen, Shaochen Zhong, Hanjie Chen, and Xia Hu. 2025. Stop overthinkin... | https://arxiv.org/abs/2505.17829v1 |
Jiafu Tang, Guanyu Li, Yiwen Ding, Wei He, Boyang Hong, Shi- han Do, Wenyu Zhan, Xiao Wang, Rui Zheng, Tao Ji, Xiaowei Shi, Yitao Zhai, Rongxiang Weng, Jingang Wang, Xunliang Cai, Tao Gui, and 5 others. 2024. Enhancing llm reasoning via critique models with test-time and training-time supervision. Preprint , arXiv:2411... | https://arxiv.org/abs/2505.17829v1 |
In this experiment, only the sub- set of English mathematical problems without images was tested, with a total of 674 ques- tions. A.2 Baselines •Greedy Search: A decoding method based on the principle of local optimality. It always selects the token with the highest current prob- ability as the output. •Self-Consisten... | https://arxiv.org/abs/2505.17829v1 |
1.31×1018 Llama3.1-8B-PRM-Deepseek-Data Reward 128 9.03×1015 Llama-3.1-70B-Instruc Auto Regressive 1 3.04×1018 Table 3: Computational Cost Analysis (in FLOPs) for Different Model Configurations during Inference. each path. We examined two primary methods for computing the final path score: •Last : Using the final step’... | https://arxiv.org/abs/2505.17829v1 |
0.1881 0.4473 0.8491 0.5160 0.2144 0.1837 0.4408 Avg. 0.8388 0.4980 0.2040 0.1807 0.4304 0.8456 0.5087 0.1936 0.1743 0.4305 128Beam 0.8484 0.5200 0.1907 0.1807 0.4350 0.8340 0.5160 0.1832 0.1807 0.4285 DVTS 0.8347 0.5260 0.2068 0.1940 0.4404 0.8499 0.5180 0.1843 0.1866 0.4347 SRCA 0.8560 0.5340 0.2497 0.2074 0.4618 0.8... | https://arxiv.org/abs/2505.17829v1 |
arXiv:2505.17832v1 [cs.CL] 23 May 2025Emerging categories in scientific explanations Giacomo Magnifico[0000−0002−1782−0668]and Eduard Barbu[0000−0002−3664−5367] Institute of Computer Science, University of Tartu, Tartu, Estonia {name.surname}@ut.ee Abstract. Clear and effective explanations are essential for human un- ... | https://arxiv.org/abs/2505.17832v1 |
and not a superimposition of pre-existing categories upon the dataset. This method, therefore, avoided pre-set criteria to explore in- stead the intrinsic connections between categories and the dataset’s sub- ject, aiming to understand the commonalities and differences within the explanations. The categories of explana... | https://arxiv.org/abs/2505.17832v1 |
K., Nematzadeh, A. (eds.) Proceed- ings of the First Workshop on Learning with Natural Language Supervision. pp. 40–47. Association for Computational Linguistics, Dublin, Ireland (May 2022). https://doi.org/10.18653/v1/2022.lnls-1.5, https://aclanthology.org/2022.lnls-1.5 7. Hayes, A., krippendorff, k.: Answering the c... | https://arxiv.org/abs/2505.17832v1 |
arXiv:2505.17833v1 [cs.CL] 23 May 2025Investigating Affect Mining Techniques for Annotation Sample Selection in the Creation of Finnish Affective Speech Corpus Kalle Lahtinen1, Einari Vaaras1, Liisa Mustanoja2, Okko R ¨as¨anen1 1Signal Processing Research Centre, Tampere University, Finland 2Language Studies, Tampere U... | https://arxiv.org/abs/2505.17833v1 |
There are a few existing Finnish cor- pora with labels for emotional content, such as [6], [7], and [8]. However, these corpora are relatively small in scale, and consist of acted speech [6, 8] or are from a very specific communica- tive setting [7]. This limits their representativeness in terms of real-world spontaneo... | https://arxiv.org/abs/2505.17833v1 |
from over 20,000 native Finnish speakers. In LP, the speakers were prompted with various everyday topics and were asked to tell about them freely (see [22]). The TP and HP datasets are sig- nificantly smaller than the LP dataset, consisting of interview recordings from the 1970’s, 1990’s and 2010’s. The original purpos... | https://arxiv.org/abs/2505.17833v1 |
hence balancing the contributions of each feature type in the distance calculations of FAFT and MAL. Our initial aim was to use FAFT in the resulting feature space to find diverse initial cluster centroids, following [7]. How- ever, the memory requirements of standard k-medoids clustering grows quadratically with the n... | https://arxiv.org/abs/2505.17833v1 |
we found that the annotators varied in their use of the rating scale, and then scaled the result back to [-1.0,1.0] with max(abs()) across all the scores for easier interpretation. The normalization significantly improved the inter-annotator agree- ment on the 2,000 sample ” gold standard ” (GS) set with five 0 1000 20... | https://arxiv.org/abs/2505.17833v1 |
of samples (clusters) to annotate. Al- ternatively, we speculated that the lack of FAFT initialization in the CLARA clustering might have caused the cluster density to follow the overall density distribution of the data, thereby aligning with random sampling from the same distribution. To study these questions, we used... | https://arxiv.org/abs/2505.17833v1 |
apparent cluster purity. We ex- perimented with the k-means, bisecting k-means, agglomerative, and CLARA clustering algorithms. For agglomerative cluster- ing, we experimented with the Euclidean, Manhattan, cosine, and Chebyshev distance metrics. These distance metrics were also tested with CLARA with the addition of P... | https://arxiv.org/abs/2505.17833v1 |
extent to which different clusters represent different emotional contents. 5. Conclusions This paper presented the FinnAffect corpus for studying affect expression and developing SER systems for spontaneous Finnish. Moreover, we introduced a pipeline for mining affect-rich speech samples for manual annotation, making u... | https://arxiv.org/abs/2505.17833v1 |
no. 9-10, pp. 1062–1087, 2011. [12] W. Fan, X. Xu, X. Xing, W. Chen, and D. Huang, “LSSED: A Large-Scale Dataset and Benchmark for Speech Emotion Recogni- tion,” in Proc. ICASSP , 2021, pp. 641–645. [13] T. Waaramaa, “Perception of emotional nonsense sentences in China, Egypt, Estonia, Finland, Russia, Sweden, and the ... | https://arxiv.org/abs/2505.17833v1 |
751–755. [28] D. Rosenkrantz, R. Stearns, and P. Lewis, “An analysis of several heuristics for the traveling salesman problem,” SICOMP , vol. 6, no. 3, pp. 563–581, 1977. [29] F. Eyben, K. R. Scherer, B. W. Schuller, J. Sundberg, E. Andr ´e, C. Busso, L. Y . Devillers, J. Epps, P. Laukka, S. S. Narayanan, and K. P. Tru... | https://arxiv.org/abs/2505.17833v1 |
Explaining Sources of Uncertainty in Automated Fact-Checking Jingyi Sun*Greta Warren*Irina Shklovski Isabelle Augenstein University of Copenhagen {jisu, grwa, ias, augenstein}@di.ku.dk Abstract Understanding sources of a model’s uncertainty regarding its predictions is crucial for effec- tive human-AI collaboration. Pr... | https://arxiv.org/abs/2505.17855v1 |
uncertainty . However , the statement in Evidence 1 , "through domestic pets." conflicts with the statement in Evidence 2 , "Notification of presumptive positive animal test results triggered a One Health* investigation by state and federal partners, who determined that no further transmission events to other animals o... | https://arxiv.org/abs/2505.17855v1 |
input segments (e.g., claim and evidence) (Ray Choudhury et al., 2023). These interactions have been shown to be both faithful to the model and plausible to humans (Sun et al., 2025). CLUE then converts these signals into uncertainty-aware explanations by explicitly discussing the interac- tions, the conflict/agreement... | https://arxiv.org/abs/2505.17855v1 |
manufacturers are "the only industry in the country" that have immunity from lawsuits Evidence: Evidence 1: No, you can't sue Pfizer ... Evidence 2: Remarks by President Biden on Gun V iolence Prevention ...Input Input Verdict: False Explanation: Colin Kaepernick is a football player , not a poker player .Input Verdict... | https://arxiv.org/abs/2505.17855v1 |
In fact-checking, supervisedmethods have been proposed that involve extracting key sentences from existing fact-checking articles and using them as explanations (Atanasova et al., 2020). Later work proposed a post-editing mecha- nism to enhance the coherence and fluency of expla- nations, (Jolly et al., 2022), while ot... | https://arxiv.org/abs/2505.17855v1 |
swer label on a specific input sequence, we follow previous work and calculate predictive uncertainty with entropy theory, which does not require multi- ple runs and is widely used in open-source models. Specifically, we define the numeric uncertainty score uas the entropy of the softmax distribution over the model’s o... | https://arxiv.org/abs/2505.17855v1 |
prompt (See App.F.1), which instructs the model to explain how the highlighted agreements or conflicts influence its confidence. Fi- nally, the standard transformer decoding process outputs both the predicted label ˆyand the accom- panying explanation YR. Attention steering. Instead of explicit instruc- tions, we can g... | https://arxiv.org/abs/2505.17855v1 |
to the model’s uncertainty, we adapt the Correlational Counterfactual Test (CCT) (Siegel et al., 2024) and propose an Entropy-CCT metric. Following Siegel et al. (2024), we begin by in- serting a random adjective or noun into the original instance Xto obtain a perturbed input X′(See App. D for details). Let u(X)denote ... | https://arxiv.org/abs/2505.17855v1 |
9), to measure the faithfulness of NLEs to the model’s uncertainty (§5.1). When rpb= 0, the explanation mentions high- and low-impact per- turbation words equally often; every +0.01adds roughly one percentage point (pp) to the chance that the explanation names a token that is truly influential for the model’s predictiv... | https://arxiv.org/abs/2505.17855v1 |
to our automatic evaluation metrics: •Helpfulness. The explanation offers informa- tion that aids readers to judge the claim and fact- check. •Coverage. The explanation captures allsalient information in the input that matters for the HealthVer DRUID Approach Faith. ( ↑) Span-Cov. ( ↑) Span-Ext. ( ↓) LEE ( ↑)Faith. ( ↑... | https://arxiv.org/abs/2505.17855v1 |
while retaining their faithfulness may therefore improve the human evaluation scores for CLUE-Span+Steering . Finally, we observed slight variation between datasets: CLUE-Span+Steering tended to be rated higher than CLUE-Span for DRUID, and vice versa for HealthVer. This may arise from differences in length and complex... | https://arxiv.org/abs/2505.17855v1 |
our evaluation with laypeople confirms that our framework produces explanations of higher quality than prompting, expert evaluations (e.g., with professional fact-checkers) are needed to as- sess practical utility in high-stakes settings. Our work is limited to the scope of explain- ing model uncertainty arising from e... | https://arxiv.org/abs/2505.17855v1 |
Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-V oss, Gretchen Krueger, Tom Henighan, Rewon Child,Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, ... | https://arxiv.org/abs/2505.17855v1 |
of mathematical statistics , 10(3):275–287. Sunnie S. Y . Kim, Q. Vera Liao, Mihaela V orvoreanu, Stephanie Ballard, and Jennifer Wortman Vaughan. 2024. "i’m not sure, but...": Examining the impact of large language models’ uncertainty expression on user reliance and trust. In Proceedings of the 2024 ACM Conference on ... | https://arxiv.org/abs/2505.17855v1 |
Schlichtkrull, Nedjma Ousidhoum, and An- dreas Vlachos. 2023. The intended uses of auto- mated fact-checking artefacts: Why, how and who. InFindings of the Association for Computational Lin- guistics: EMNLP 2023 , pages 8618–8642, Singapore. Association for Computational Linguistics. Vera Schmitt, Luis-Felipe Villa-Are... | https://arxiv.org/abs/2505.17855v1 |
Language Process- ing, pages 5433–5442, Singapore. Association for Computational Linguistics. Jasper van der Waa, Tjeerd Schoonderwoerd, Jurri- aan van Diggelen, and Mark Neerincx. 2020. In- terpretable confidence measures for decision support systems. International Journal of Human-Computer Studies , 144:102493. Thoma... | https://arxiv.org/abs/2505.17855v1 |
Lingzhi Wang, Zhanghao Wang, Hong Cheng, Rui Zhang, and Kam-Fai Wong. 2024. PACAR: Automated Fact-Checking with Planning and Customized Action Reasoning Using Large Lan- guage Models. In Proceedings of the 2024 Joint International Conference on Computational Linguis- tics, Language Resources and Evaluation (LREC- COLIN... | https://arxiv.org/abs/2505.17855v1 |
. 3. Output the span pairs exactly as given , followed by " relation : agree | disagree | unrelated ". Return format : 1. " SPAN A" - " SPAN B" relation : <agree | disagree | unrelated > 2. ... 3. ... ### SHOT 1 ( annotated example ) Claim : [...] Evidence 1: [...] Evidence 2: [...] Span interactions (to be labelled ):... | https://arxiv.org/abs/2505.17855v1 |
the three most influential span interactions from Claim - Evidence 1, Claim - Evidence 2, and Evidence 1- Evidence 2, and describing how each interaction ’s relation (agree , disagree , or unrelated ) affects your overall confidence . Return format : [ Prediction ] [ Explanation ] ### SHOT 1 Input Claim : [...] Evidenc... | https://arxiv.org/abs/2505.17855v1 |
Figure 5: Three-shot prompt for CLUE-Span and CLUE-Span+Steering (Shots 2–3 omitted) on the HEALTH VERand D RUID datasets. turbations each (see App. D). and (iv) demonstrat- ing through concise numerical summaries that both CLUE-Span andCLUE-Span+Steering are signifi- cantly more faithful than the Prompt Baseline . G.1... | https://arxiv.org/abs/2505.17855v1 |
mance. Each participant evaluated explanations for 10 instances (5 labelled ‘True’, 5 labelled ‘False’), in addition to two attention check instances which were used to screen responses for quality. Procedure Participants read information about the study (see H.3) and provided informed con- sent (see H.4) before readin... | https://arxiv.org/abs/2505.17855v1 |
how to interpret the true/false prediction. We ask you to evaluate the explanations along 5 different dimensions (the detailed explana- tion of the task is on the next page). All participants who complete the survey will receive a payment of £3. There is no cost to you for participating. You may refuse to participate o... | https://arxiv.org/abs/2505.17855v1 |
process my data as part of the Human-Centred Explainable Fact Checking project. •I understand that any data I provide will be anony- mous and not identifiable to me. •I understand that my anonymous response data will be retained by the study team. •I understand that after I submit my responses at the end of the study, ... | https://arxiv.org/abs/2505.17855v1 |
that is helpful for evaluating the claim and the fact check. Coverage. The explanation contains important, salient information and does not miss any impor- tant points that contribute to the fact check. Non-redundancy. The explanation does not contain any information that is redundant/repeat- ed/not relevant to the cla... | https://arxiv.org/abs/2505.17855v1 |
arXiv:2505.17870v1 [cs.CL] 23 May 2025Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods Shaina Raza1∗Rizwan Qureshi2Marcelo Lotif1Aman Chadha3† Deval Pandya1Christos Emmanouilidis4 1Vector Institute, Toronto, Canada2University of Central Florida, Orlando, USA 3Amazon Web Services4Unive... | https://arxiv.org/abs/2505.17870v1 |
as exposure to a weakened pathogen enables the immune system to recognize and neutralize future threats, controlled exposure of an AI model to explicitly labeled false information can help it identify and resist misleading patterns (see Figure 1 for a schematic analogy). Rather than treating false data as toxic and avo... | https://arxiv.org/abs/2505.17870v1 |
(b)Method-by-property matrix: Defense techniques characterized by input type, goals, control, and risk. Technique Input Type Goal Control Risk Adversarial Training perturbations robustness curated low Data Poisoning unlabeled false data corrupt model malicious high RLHF human preferences alignment curated medium Model ... | https://arxiv.org/abs/2505.17870v1 |
a deliberate, transparent training strategy by the model developers, where false information is clearly labeled as false. The goal is the opposite of poisoning: instead of corrupting the model, it aims to strengthen the model against falsehoods. The falsehood “dose” is curated and limited in model immunization in the t... | https://arxiv.org/abs/2505.17870v1 |
generators) to mimic real-world misinformation. This ensures broad coverage of misinformation variants that may not be captured in existing real-world examples, enhancing the diversity of the “falsehood repository”. All collected and generated false statements are then isolated in a secure quarantine step: they are sto... | https://arxiv.org/abs/2505.17870v1 |
achieved. 4.Deployment & Monitoring: Once validation confirms that the model meets performance and robustness targets, the immunized model is released to production. In this final stage (bottom most portion of Figure 4), several deployment-time safeguards and ongoing monitoring mechanisms are put in place to maintain t... | https://arxiv.org/abs/2505.17870v1 |
immunization. •Continuous Accountability: Establish channels for ongoing oversight even after deployment. For example, maintain public or third-party audit mechanisms where users or auditors can report cases where the model might be propagating an unrecognized falsehood. Logging the model’s outputs and decisions enable... | https://arxiv.org/abs/2505.17870v1 |
model in Figure 6 that shows the baseline model an- swered only about 60% of the misinformation-laden queries correctly (or safely). It often fell for traps – for instance, when asked about a conspiracy, the baseline might repeat parts of it or give a confused response. In contrast, the immunized model truthful respons... | https://arxiv.org/abs/2505.17870v1 |
observed hints of this in our qualitative testing (see Table1): the immunized model correctly handled some misinformation prompts that were not in its training set, seemingly by using reasoning or analogical patterns. However, this aspect needs systematic study. It relates to the broader issue of out-of-distribution ro... | https://arxiv.org/abs/2505.17870v1 |
one has seen before), other strategies are needed, such as the model’s own ability to fact-check on the fly or continued human oversight. Human Factors: Making AI more resistant to misinformation is not only a technical goal but also a socio-technical one. A model that simply refuses to answer or bluntly corrects the u... | https://arxiv.org/abs/2505.17870v1 |
is a relatively lightweight addition to the training process (using modest amounts of curated data), yet it yielded a significant boost in truthfulness in our experiments. Moreover, it embodies a preventative philosophy for AI safety. Through model immunization, AI developers can proactively reduce the risk of their sy... | https://arxiv.org/abs/2505.17870v1 |
Lohia, J. Martino, and S. Mehta. AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias. IBM Journal of Research and Development , 63(4-5), 2019. [3]Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindn... | https://arxiv.org/abs/2505.17870v1 |
Dolatabadi, and Deval Pandya. Fair enough: Develop and assess a fair-compliant dataset for large language model training? Data Intelligence , 6(2):559–585, 2024. [23] Shaina Raza, Rizwan Qureshi, Anam Zahid, Joseph Fioresi, Ferhat Sadak, Muhammad Saeed, Ranjan Sapkota, Aditya Jain, Anas Zafar, Muneeb Ul Hassan, et al. ... | https://arxiv.org/abs/2505.17870v1 |
, 2024. A Related Work Proactive Factuality Training A growing body of work addresses LLM factuality and hallucina- tions. Conventional fine-tuning on fact-checked or truthful datasets can improve a model’s correctness on specific benchmarks, but these approaches typically focus on teaching more truth rather than expli... | https://arxiv.org/abs/2505.17870v1 |
26] in human misinformation research, where exposing people to weakened doses of misinformation (or common misinformation techniques) can “prebunk” them against future falsehoods. Model immunization can be seen as bringing this inoculation principle into AI training. To our knowledge, no prior work has explicitly used ... | https://arxiv.org/abs/2505.17870v1 |
statements (with false labels) + nor- mal dataAdversarially perturbed inputs (worst-case ex- amples) [18]No added training data; uses human feedback on out- puts [21]No change to base training data; uses separate detection model [17, 22] Goal Inoculate model against falsehoods to improve truthfulnessResist malicious in... | https://arxiv.org/abs/2505.17870v1 |
oversight plans for high-risk systems.Enforceable fines drive adoption of best prac- tices; harmonises stan- dards across EU.Compliance burden on SMEs; possible chilling effects on creative ex- pression; limited reach outside EU. Table 4: Ethical principles and corresponding safeguards in model immunization. Ethical Pr... | https://arxiv.org/abs/2505.17870v1 |
arXiv:2505.17873v1 [cs.CL] 23 May 2025MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback Wanhao Liu1,2∗, Zonglin Yang3,2∗, Jue Wang1, Lidong Bing4, Di Zhang2, Dongzhan Zhou2,Yuqiang Li2†,Houqiang Li1†,Erik Cambria3†,Wanli Ouyang2† 1University of Science and Technology of China2... | https://arxiv.org/abs/2505.17873v1 |
space where the x-axis (potentially multidimensional) parameterizes candidate hypotheses, such that each coordinate corresponds to a distinct hypothesis variant, and the y-axis denotes the associated experimental feed- back (e.g., performance). Assumption 1 ( A1) posits that within any sufficiently local neighborhood o... | https://arxiv.org/abs/2505.17873v1 |
we propose a new task: developing more accurate simulators for experimental feedback. Using the simulator to approximate experimental outcomes, we develop an pseudo experiment-guided ranking method leveraging functional clustering of hypotheses. Clustering enables effective transfer of insights from previously tested h... | https://arxiv.org/abs/2505.17873v1 |
assessed by scientists or LLMs—may not accurately reflect functional similarity. For example, a chemical hypothesis may include a useful functional component whose contribution is not fully recognized, causing it to be placed farther from the dominant peak than it should be—resulting in a spurious secondary peak. Conve... | https://arxiv.org/abs/2505.17873v1 |
is to construct an embedding function ϕ(·) that maps each hypothesis hinto a latent space such that distances in this space reflect meaningful functional differences. Through extensive discussions with chemistry PhD students, we observe that a chemical hypothesis succeeds in addressing a research question primarily due... | https://arxiv.org/abs/2505.17873v1 |
et al., 2024b) and ground-truth hypotheses from top-tier chemistry journals reporting high-quality lab experiments. The goal of experiment- 5 Clustering Extracted ComponentsPerforming Accumulated AnalysisSelecting HypothesisSelecting ClusterSimulating ExperimentExtracting &Classifying Key Components Experiment Result 1... | https://arxiv.org/abs/2505.17873v1 |
evaluate the effectiveness of the chosen cluster and to validate or update the mechanistic assumptions made. Step 4: Iterative Summarization and Refinement. Following each experimental evaluation, a detailed analysis is conducted, and the insights gained are integrated into a cumulative summary. This continually update... | https://arxiv.org/abs/2505.17873v1 |
the lowest RMSE of 0.213. Compared to the Matched Score baseline, CSX-Sim demonstrates substantial improvements in both trend alignment (+0.117 in Spearman) and robustness (+14 in PCI), while also reducing predictive error. Ablation studies further highlight the importance of critical component identification: removing... | https://arxiv.org/abs/2505.17873v1 |
perspective, we systematically introduce controlled distortions that worsen simulator fidelity from an optimization standpoint. Specifically, we collaborated with chemistry PhD students to design three types of distortions commonly encountered in chemical research: local maxima/minima, plateaus, and cliffs. These noise... | https://arxiv.org/abs/2505.17873v1 |
access to real experimental feedback. By formalizing three foundational assumptions, we develop a high-fidelity simulator that approximates experimental 9 outcomes based on hypothesis similarity, validated against a curated dataset of 124 hypotheses with reported wet-lab results. Building on this simulator, our propose... | https://arxiv.org/abs/2505.17873v1 |
A Extracting Key Chemical Components in the Simulator A.1 A Framework for Extracting Critical Chemical Components in the Simulator To better illustrate the specific framework of CSX-Sim for extracting key chemical components, as shown in Figure 5. For scientific hypotheses addressing specific problems, we categorize ke... | https://arxiv.org/abs/2505.17873v1 |
the role and function of the substance or method, including a detailed mechanistic explanation of how it addresses the scientific question and enhances relevant properties. Chemical substance/component/method 2 Role and Function: Describe the role and function of the substance or method, including a detailed mechanisti... | https://arxiv.org/abs/2505.17873v1 |
0.7 mV K−1and ionic conductivity improved by 20%. Mechanical tests reveal significant strength with a tensile strain at break of 350% and the system maintains stability under various mechanical deformations. This approach offers a cost-effective, adaptable solution for low-grade heat harvesting. Here’s Chemistry Expert... | https://arxiv.org/abs/2505.17873v1 |
missing only one: “Polyvinyl Alcohol (PV A) as the Hydrogel Matrix.” The points it does identify align accurately with those proposed by the human expert based on the hypothesis, demonstrating the high accuracy of CSX-Sim in extracting key chemical components. B The Role of CriticalPoints in CSX-Sim To better illustrat... | https://arxiv.org/abs/2505.17873v1 |
Hypothesis identifies three core key points: Gelatin, KCl (Potassium Chloride), and the [Fe(CN) 6]3−/[Fe(CN) 6]4−Redox Pair, each playing significant roles in enhancing the Seebeck coefficient for thermoelectric efficiency. The Generated Hypothesis uses Polyacrylamide (PAM) in place of Gelatin, which can provide a simi... | https://arxiv.org/abs/2505.17873v1 |
test set reflects the diversity and complexity of real-world chemical experiments, enhancing the robustness of our evaluation. A statistical analysis of the 124 authentic wet lab results was conducted to rigorously evaluate the simulator’s performance. By including a substantial number of experiments from various subfi... | https://arxiv.org/abs/2505.17873v1 |
a versatile tool, offering reliable predictions that can support a wide range of chemical research and applications. 16 1 2 3 4 5 60.00.20.40.60.81.0Normalized Experimental Results Order of Experimental Results Real Experimental Data CSX-SimulatorFigure 6: Comparison of simulated real experimental results with CSX-Simu... | https://arxiv.org/abs/2505.17873v1 |
0.064 0.174 0.159 w/o ComponentExtraction 0.087 0.215 0.192 Table 6: Validating the simulator with collected chemistry experiment results from literature. Below, we define each metric used in the evaluation, along with their respective formulas, to ensure scientific rigor: Mean Squared Error (MSE): MSE measures the ave... | https://arxiv.org/abs/2505.17873v1 |
the occurrence of these distortions in different scenarios and sorted them by frequency, from low to high. Based on this distribution, we categorized the discrepancies: the top 35% of ob- served gaps were classified as Simple Noise, the middle 40% as Moderate Noise, and the bottom 25% as Complex Noise. Furthermore, we ... | https://arxiv.org/abs/2505.17873v1 |
the internal reasoning of large language models, lacking integration with empirical experimental outcomes. In contrast, we introduce the novel task of experiment-guided ranking, designed to prioritize candidate hypotheses by leveraging insights from previously tested results. However, the development of such strategies... | https://arxiv.org/abs/2505.17873v1 |
Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model Khalil Hennara, Muhammad Hreden, Mohamed Motaism Hamed, Zeina Aldallal, Sara Chrouf, and Safwan AlModhayan Khobar, Saudi Arabia hennara,hreden,hamed,aldallal,chrouf,safwan@misraj.ai Abstract We introduce Mutarjim , a compact yet po... | https://arxiv.org/abs/2505.17894v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.