Lidong Bing · page 2
Papers
- Contrastive Chain-of-Thought Prompting (2023 · 45 citations)
Chain-of-thought (CoT) prompting helps large language models reason. However, earlier work found that demonstrations with flawed logic perform almost as well as correct ones, and standard CoT never shows a model which errors to avoid. The authors propose contrastive chain of thought, in which each few-shot example… - M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework (2025 · 21 citations)
Question answering over real-world documents is difficult for large multimodal models. Such documents can run to hundreds of pages and mix text, figures and tables. Earlier benchmarks mostly used documents under 50 pages and short extractive answers. - Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions (2025 · 16 citations)
Keeping up with rapidly released LLMs requires evaluation that is both fast and trustworthy. Static benchmarks such as MMLU or MT-Bench risk contamination and handle open-ended output poorly. Crowdsourced platforms like Chatbot Arena are trusted but need many human votes, which makes them slow for new models and weak… - Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks (2025 · 13 citations)
LLMs that combine chain-of-thought with retrieval-augmented generation often fail on hard, knowledge-heavy problems such as competitive programming. - 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models (2025 · 9 citations)
DeepSeek-R1 showed that explicit step-by-step reasoning can be trained into language models cheaply. However, DeepSeek did not publish full recipes, training data or configurations for DeepSeek-R1-Zero, DeepSeek-R1 or the distilled models. This survey collects the open replication efforts that appeared in the roughly… - Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers (2025 · 8 citations)
Open multilingual LLMs tend to favor languages with abundant web text, such as French or German. Populous but data-poor languages like Hindi, Bengali or Urdu remain underserved. Babel, from Alibaba's DAMO Academy, targets the 25 languages with the most speakers, which together cover roughly 7 billion people. - FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving (2025 · 6 citations)
Most reasoning benchmarks for LLMs score only the final answer. They do not show whether a model can examine its intermediate steps, notice a dead end, and recover from it. FineReason fills this gap with logic puzzles that break down into small verifiable steps. It covers four puzzle types: Sudoku, Graph Coloring…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/lidong-bing/page/2/