add citations

Signed-off-by: Yotam-Perlitz <y.perlitz@ibm.com>

app.py

@@ -493,6 +493,270 @@ with st.expander(label="Model scored by the aggragate"):
         use_container_width=True,
     )
 
+with st.expander(label="Citations"):
+    st.code("""
+    @misc{liu2023agentbenchevaluatingllmsagents,
+        title={AgentBench: Evaluating LLMs as Agents}, 
+        author={Xiao Liu and Hao Yu and Hanchen Zhang and Yifan Xu and Xuanyu Lei and Hanyu Lai and Yu Gu and Hangliang Ding and Kaiwen Men and Kejuan Yang and Shudan Zhang and Xiang Deng and Aohan Zeng and Zhengxiao Du and Chenhui Zhang and Sheng Shen and Tianjun Zhang and Yu Su and Huan Sun and Minlie Huang and Yuxiao Dong and Jie Tang},
+        year={2023},
+        eprint={2308.03688},
+        archivePrefix={arXiv},
+        primaryClass={cs.AI},
+        url={https://arxiv.org/abs/2308.03688}, 
+}
+            
+    @software{Li_AlpacaEval_An_Automatic_2023,
+        author = {Li, Xuechen and Zhang, Tianyi and Dubois, Yann and Taori, Rohan and Gulrajani, Ishaan and Guestrin, Carlos and Liang, Percy and Hashimoto, Tatsunori B.},
+        month = may,
+        title = {{AlpacaEval: An Automatic Evaluator of Instruction-following Models}},
+        year = {2023}
+    }
+            
+    @misc{li2024crowdsourceddatahighqualitybenchmarks,
+        title={From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline}, 
+        author={Tianle Li and Wei-Lin Chiang and Evan Frick and Lisa Dunlap and Tianhao Wu and Banghua Zhu and Joseph E. Gonzalez and Ion Stoica},
+        year={2024},
+        eprint={2406.11939},
+        archivePrefix={arXiv},
+        primaryClass={cs.LG},
+        url={https://arxiv.org/abs/2406.11939}, 
+    }
+    @misc{chiang2024chatbot,
+        title={Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference},
+        author={Wei-Lin Chiang and Lianmin Zheng and Ying Sheng and Anastasios Nikolas Angelopoulos and Tianle Li and Dacheng Li and Hao Zhang and Banghua Zhu and Michael Jordan and Joseph E. Gonzalez and Ion Stoica},
+        year={2024},
+        eprint={2403.04132},
+        archivePrefix={arXiv},
+        primaryClass={cs.AI}
+    }
+    @misc{arenahard2024,
+        title = {From Live Data to High-Quality Benchmarks: The Arena-Hard Pipeline},
+        url = {https://lmsys.org/blog/2024-04-19-arena-hard/},
+        author = {Tianle Li*, Wei-Lin Chiang*, Evan Frick, Lisa Dunlap, Banghua Zhu, Joseph E. Gonzalez, Ion Stoica},
+        month = {April},
+        year = {2024}
+    }
+            
+    @misc{kim2024biggenbenchprincipledbenchmark,
+        title={The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models}, 
+        author={Seungone Kim and Juyoung Suk and Ji Yong Cho and Shayne Longpre and Chaeeun Kim and Dongkeun Yoon and Guijin Son and Yejin Cho and Sheikh Shafayat and Jinheon Baek and Sue Hyun Park and Hyeonbin Hwang and Jinkyung Jo and Hyowon Cho and Haebin Shin and Seongyun Lee and Hanseok Oh and Noah Lee and Namgyu Ho and Se June Joo and Miyoung Ko and Yoonjoo Lee and Hyungjoo Chae and Jamin Shin and Joel Jang and Seonghyeon Ye and Bill Yuchen Lin and Sean Welleck and Graham Neubig and Moontae Lee and Kyungjae Lee and Minjoon Seo},
+        year={2024},
+        eprint={2406.05761},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2406.05761}, 
+    }
+                
+    @misc{liang2023holisticevaluationlanguagemodels,
+        title={Holistic Evaluation of Language Models}, 
+        author={Percy Liang and Rishi Bommasani and Tony Lee and Dimitris Tsipras and Dilara Soylu and Michihiro Yasunaga and Yian Zhang and Deepak Narayanan and Yuhuai Wu and Ananya Kumar and Benjamin Newman and Binhang Yuan and Bobby Yan and Ce Zhang and Christian Cosgrove and Christopher D. Manning and Christopher Ré and Diana Acosta-Navas and Drew A. Hudson and Eric Zelikman and Esin Durmus and Faisal Ladhak and Frieda Rong and Hongyu Ren and Huaxiu Yao and Jue Wang and Keshav Santhanam and Laurel Orr and Lucia Zheng and Mert Yuksekgonul and Mirac Suzgun and Nathan Kim and Neel Guha and Niladri Chatterji and Omar Khattab and Peter Henderson and Qian Huang and Ryan Chi and Sang Michael Xie and Shibani Santurkar and Surya Ganguli and Tatsunori Hashimoto and Thomas Icard and Tianyi Zhang and Vishrav Chaudhary and William Wang and Xuechen Li and Yifan Mai and Yuhui Zhang and Yuta Koreeda},
+        year={2023},
+        eprint={2211.09110},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2211.09110}, 
+    }
+
+
+    @misc{open-llm-leaderboard-v2,
+    author = {Clémentine Fourrier and Nathan Habib and Alina Lozovskaya and Konrad Szafer and Thomas Wolf},
+    title = {Open LLM Leaderboard v2},
+    year = {2024},
+    publisher = {Hugging Face},
+    howpublished = "\url{https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard}",
+    }
+
+    @software{eval-harness,
+        author       = {Gao, Leo and
+                        Tow, Jonathan and
+                        Biderman, Stella and
+                        Black, Sid and
+                        DiPofi, Anthony and
+                        Foster, Charles and
+                        Golding, Laurence and
+                        Hsu, Jeffrey and
+                        McDonell, Kyle and
+                        Muennighoff, Niklas and
+                        Phang, Jason and
+                        Reynolds, Laria and
+                        Tang, Eric and
+                        Thite, Anish and
+                        Wang, Ben and
+                        Wang, Kevin and
+                        Zou, Andy},
+        title        = {A framework for few-shot language model evaluation},
+        month        = sep,
+        year         = 2021,
+        publisher    = {Zenodo},
+        version      = {v0.0.1},
+        doi          = {10.5281/zenodo.5371628},
+        url          = {https://doi.org/10.5281/zenodo.5371628},
+    }
+
+    @misc{zhou2023instructionfollowingevaluationlargelanguage,
+        title={Instruction-Following Evaluation for Large Language Models},
+        author={Jeffrey Zhou and Tianjian Lu and Swaroop Mishra and Siddhartha Brahma and Sujoy Basu and Yi Luan and Denny Zhou and Le Hou},
+        year={2023},
+        eprint={2311.07911},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2311.07911},
+    }
+
+    @misc{suzgun2022challengingbigbenchtaskschainofthought,
+        title={Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them},
+        author={Mirac Suzgun and Nathan Scales and Nathanael Schärli and Sebastian Gehrmann and Yi Tay and Hyung Won Chung and Aakanksha Chowdhery and Quoc V. Le and Ed H. Chi and Denny Zhou and Jason Wei},
+        year={2022},
+        eprint={2210.09261},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2210.09261},
+    }
+
+    @misc{hendrycks2021measuringmathematicalproblemsolving,
+        title={Measuring Mathematical Problem Solving With the MATH Dataset},
+        author={Dan Hendrycks and Collin Burns and Saurav Kadavath and Akul Arora and Steven Basart and Eric Tang and Dawn Song and Jacob Steinhardt},
+        year={2021},
+        eprint={2103.03874},
+        archivePrefix={arXiv},
+        primaryClass={cs.LG},
+        url={https://arxiv.org/abs/2103.03874},
+    }
+
+    @misc{rein2023gpqagraduatelevelgoogleproofqa,
+        title={GPQA: A Graduate-Level Google-Proof Q&A Benchmark},
+        author={David Rein and Betty Li Hou and Asa Cooper Stickland and Jackson Petty and Richard Yuanzhe Pang and Julien Dirani and Julian Michael and Samuel R. Bowman},
+        year={2023},
+        eprint={2311.12022},
+        archivePrefix={arXiv},
+        primaryClass={cs.AI},
+        url={https://arxiv.org/abs/2311.12022},
+    }
+
+    @misc{sprague2024musrtestinglimitschainofthought,
+        title={MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning},
+        author={Zayne Sprague and Xi Ye and Kaj Bostrom and Swarat Chaudhuri and Greg Durrett},
+        year={2024},
+        eprint={2310.16049},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2310.16049},
+    }
+
+    @misc{wang2024mmluprorobustchallengingmultitask,
+        title={MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark},
+        author={Yubo Wang and Xueguang Ma and Ge Zhang and Yuansheng Ni and Abhranil Chandra and Shiguang Guo and Weiming Ren and Aaran Arulraj and Xuan He and Ziyan Jiang and Tianle Li and Max Ku and Kai Wang and Alex Zhuang and Rongqi Fan and Xiang Yue and Wenhu Chen},
+        year={2024},
+        eprint={2406.01574},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2406.01574},
+    }
+
+    @misc{open-llm-leaderboard-v1,
+        author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
+        title = {Open LLM Leaderboard (2023-2024)},
+        year = {2023},
+        publisher = {Hugging Face},
+        howpublished = "\url{https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard}"
+    }
+            
+    @misc{open-llm-leaderboard,
+        author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
+        title = {Open LLM Leaderboard},
+        year = {2023},
+        publisher = {Hugging Face},
+        howpublished = "\url{https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard}"
+    }
+
+    @misc{waldis2024holmesbenchmarklinguisticcompetence,
+        title={Holmes: Benchmark the Linguistic Competence of Language Models}, 
+        author={Andreas Waldis and Yotam Perlitz and Leshem Choshen and Yufang Hou and Iryna Gurevych},
+        year={2024},
+        eprint={2404.18923},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2404.18923}, 
+    }       
+
+    @article{livebench,
+        author    = {White, Colin and Dooley, Samuel and Roberts, Manley and Pal, Arka and Feuer, Ben and Jain, Siddhartha and Shwartz-Ziv, Ravid and Jain, Neel and Saifullah, Khalid and Naidu, Siddartha and Hegde, Chinmay and LeCun, Yann and Goldstein, Tom and Neiswanger, Willie and Goldblum, Micah},
+        title     = {LiveBench: A Challenging, Contamination-Free LLM Benchmark},
+        url       = {arXiv preprint arXiv:2406.19314},
+        year      = {2024},
+    }  
+            
+    @article{ni2024mixeval,
+        title={MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures},
+        author={Ni, Jinjie and Xue, Fuzhao and Yue, Xiang and Deng, Yuntian and Shah, Mahir and Jain, Kabir and Neubig, Graham and You, Yang},
+        journal={arXiv preprint arXiv:2406.06565},
+        year={2024}
+    }
+            
+    @misc{wang2024mmluprorobustchallengingmultitask,
+        title={MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark}, 
+        author={Yubo Wang and Xueguang Ma and Ge Zhang and Yuansheng Ni and Abhranil Chandra and Shiguang Guo and Weiming Ren and Aaran Arulraj and Xuan He and Ziyan Jiang and Tianle Li and Max Ku and Kai Wang and Alex Zhuang and Rongqi Fan and Xiang Yue and Wenhu Chen},
+        year={2024},
+        eprint={2406.01574},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2406.01574}, 
+    }
+                
+    @misc{zheng2023judgingllmasajudgemtbenchchatbot,
+        title={Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena}, 
+        author={Lianmin Zheng and Wei-Lin Chiang and Ying Sheng and Siyuan Zhuang and Zhanghao Wu and Yonghao Zhuang and Zi Lin and Zhuohan Li and Dacheng Li and Eric P. Xing and Hao Zhang and Joseph E. Gonzalez and Ion Stoica},
+        year={2023},
+        eprint={2306.05685},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL},
+        url={https://arxiv.org/abs/2306.05685}, 
+    }
+            
+    @misc{2023opencompass,
+        title={OpenCompass: A Universal Evaluation Platform for Foundation Models},
+        author={OpenCompass Contributors},
+        howpublished = {\url{https://github.com/open-compass/opencompass}},
+        year={2023}
+    }
+            
+    @misc{qin2023toolllm,
+        title={ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs}, 
+        author={Yujia Qin and Shihao Liang and Yining Ye and Kunlun Zhu and Lan Yan and Yaxi Lu and Yankai Lin and Xin Cong and Xiangru Tang and Bill Qian and Sihan Zhao and Runchu Tian and Ruobing Xie and Jie Zhou and Mark Gerstein and Dahai Li and Zhiyuan Liu and Maosong Sun},
+        year={2023},
+        eprint={2307.16789},
+        archivePrefix={arXiv},
+        primaryClass={cs.AI}
+    }
+                
+    @misc{qin2023tool,
+        title={Tool Learning with Foundation Models}, 
+        author={Yujia Qin and Shengding Hu and Yankai Lin and Weize Chen and Ning Ding and Ganqu Cui and Zheni Zeng and Yufei Huang and Chaojun Xiao and Chi Han and Yi Ren Fung and Yusheng Su and Huadong Wang and Cheng Qian and Runchu Tian and Kunlun Zhu and Shihao Liang and Xingyu Shen and Bokai Xu and Zhen Zhang and Yining Ye and Bowen Li and Ziwei Tang and Jing Yi and Yuzhang Zhu and Zhenning Dai and Lan Yan and Xin Cong and Yaxi Lu and Weilin Zhao and Yuxiang Huang and Junxi Yan and Xu Han and Xian Sun and Dahai Li and Jason Phang and Cheng Yang and Tongshuang Wu and Heng Ji and Zhiyuan Liu and Maosong Sun},
+        year={2023},
+        eprint={2304.08354},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL}
+    }
+                
+    @misc{guo2024stabletoolbench,
+        title={StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models},
+        author={Guo, Zhicheng and Cheng, Sijie and Wang, Hao and Liang, Shihao and Qin, Yujia and Li, Peng and Liu, Zhiyuan and Sun, Maosong and Liu, Yang},
+        year={2024},
+        eprint={2403.07714},
+        archivePrefix={arXiv},
+        primaryClass={cs.CL}
+    }
+            
+    @article{yuchen2024wildbench,
+        title={WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild},
+        author={Yuchen Lin, Bill and Deng, Yuntian and Chandu, Khyathi and Brahman, Faeze and Ravichander, Abhilasha and Pyatkin, Valentina and Dziri, Nouha and Le Bras, Ronan and Choi, Yejin},
+        journal={arXiv e-prints},
+        pages={arXiv--2406},
+        year={2024}
+    }
+    
+""")
+)
 
 st.markdown(
     "BenchBench-Leaderboard complements our study, where we analyzed over 40 prominent benchmarks and introduced standardized practices to enhance the robustness and validity of benchmark evaluations through the [BenchBench Python package](#). "