6 citations · 21 across the 25 of their papers we have counts for
31 papers
Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning
Jingwei Ni, Dmitry Abulkhanov, Vladislav Smirnov +5
Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a metareason…
Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining
Yongan Yu, Shantam Raj, Jingwei Ni +3
Natural Language Processing (NLP) in the climate domain requires models to process heterogeneous text sources, including scientific literature, policy disclosures, and synthetic re…
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Siyuan Huang, Pengyu Cheng, Haotian Liu +10
LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task…
REKEY: Metadata-Grounded Visual-Key Regeneration for Contamination-Resilient VQA Evaluation
Tengjie Lin, Yutao Sun, Jingwei Ni +7
Static visual question answering (VQA) benchmarks age quickly: Once the items leak into training corpora, scores can reflect memorization rather than genuine visual ability, thus o…
GDPO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
Haotian Liu, Yihao Liu, Jingwei Ni +11
As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorith…
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
Vladislav Smirnov, Chieu Nguyen, Sergey Senichev +14
Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via m…
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Tao Chen, Gangwei Jiang, Pengyu Cheng +10
Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current rew…
Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation
Minjing Shi, Junling Wang, Jingwei Ni +2
Identifying logical fallacies in everyday discourse is challenging for many people. This challenge is amplified in the era of Large Language Models (LLMs), where malicious agents c…
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Jingwei Ni, Yihao Liu, Xinpeng Liu +7
Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually authoring such skills does not scale, and skills generated purely from parametric knowle…
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
Mubashara Akhtar, Anka Reuel, Prajna Soni +34
Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult…
pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs
Tobias Schimanski, Imene Kolli, Yu Fan +4
PDFs are the second-most used document type on the internet (after HTML). Yet, existing QA datasets commonly start from text sources or only address specific domains. In this paper…
ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu +8
LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate…
WeatherArchive-Bench: Benchmarking Retrieval-Augmented Reasoning for Historical Weather Archives
Yongan Yu, Xianda Du, Qingchen Hu +7
Historical archives on weather events are collections of enduring primary source records that offer rich, untapped narratives of how societies have experienced and responded to ext…
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
Project Apertus, Alejandro Hernández-Cano, Alexander Hägele +100
We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingu…
Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification
Chenfei Xiong, Jingwei Ni, Yu Fan +10
We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic…
Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?
Jingwei Ni, Yu Fan, Vilém Zouhar +6
Variation in human annotation (i.e., disagreements) is common in NLP, often reflecting important information like task subjectivity and sample ambiguity. Modeling this variation is…
LEXam: Benchmarking Legal Reasoning on 340 Law Exams
Yu Fan, Jingwei Ni, Jakob Merane +14
Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce LEXam, a novel be…
Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning
Tianyi Wu, Jingwei Ni, Bryan Hooi +5
Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to…
DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation
Jingwei Ni, Tobias Schimanski, Meihong Lin +3
Retrieval Augmented Generation (RAG) is widely employed to ground responses to queries on domain-specific documents. But do RAG implementations leave out important information when…
ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures
Tobias Schimanski, Jingwei Ni, Roberto Spacey +2
To handle the vast amounts of qualitative data produced in corporate climate communication, stakeholders increasingly rely on Retrieval Augmented Generation (RAG) systems. However,…
AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
Jingwei Ni, Minjing Shi, Dominik Stammbach +3
With the rise of generative AI, automated fact-checking methods to combat misinformation are becoming more and more important. However, factual claim detection, the first step in a…
Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering
Tobias Schimanski, Jingwei Ni, Mathias Kraus +2
Advances towards more faithful and traceable answers of Large Language Models (LLMs) are crucial for various research and practical endeavors. One avenue in reaching this goal is b…
Automated Fact-Checking of Climate Change Claims with Large Language Models
Markus Leippold, Saeid Ashraf Vaghefi, Dominik Stammbach +10
This paper presents Climinator, a novel AI-based tool designed to automate the fact-checking of climate change claims. Utilizing an array of Large Language Models (LLMs) informed b…