Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought (CoT). Distillation post-training on LRMs-generated data is a straightforward yet effective method to enhance the reasoning abilities of smaller models, but faces a critical bottleneck: we found that distilled long CoT data poses learning difficulty for small models and leads to the inheritance of biases (i.e., formalistic long-time thinking) when using Supervised Fine-tuning (SFT) and Reinforcement Learning (RL) methods. To alleviate this bottleneck, we propose constructing data from scratch using Monte Carlo Tree Search (MCTS). We then exploit a set of CoT-aware approaches, including Thoughts Length Balance, Fine-grained DPO, and Joint Post-training Objective, to enhance SFT and RL on the MCTS data. We conducted evaluation on various benchmarks such as math (GSM8K, MATH, AIME). instruction-following (Multi-IF) and planning (Blocksworld), results demonstrate our CoT-aware approaches substantially improve the reasoning performance of distilled models compared to standard distilled models via reducing the hallucinations in long-time thinking.

Instruction-following capability has become a major ability to be evaluated for Large Language Models. However, existing datasets, such as IFEval, are either predominantly monolingual and centered on English or simply machine translated to other languages, limiting their applicability in multilingual contexts. In this paper, we present an carefully-curated extension of IFEval to a localized multilingual version named Marco-Bench-MIF, covering 30 languages with varying levels of localization. Our benchmark addresses linguistic constraints (e.g., modifying capitalization requirements for Chinese) and cultural references (e.g., substituting region-specific company names in prompts) via a hybrid pipeline combining translation with verification. Through comprehensive evaluation of 20+ LLMs on our Marco-Bench-MIF, we found that: (1) 25-35% accuracy gap between high/low-resource languages, (2) model scales largely impact performance by 45-60% yet persists script-specific challenges, and (3) machine-translated data underestimates accuracy by 7-22% versus localized data. Our analysis identifies challenges in multilingual instruction following, including keyword consistency preservation and compositional constraint adherence across languages. Our Marco-Bench-MIF will be made publicly available to the community.

“Recent efforts have evaluated large language models (LLMs) in areas such as com-monsense reasoning, mathematical reasoning, and code generation. However, to thebest of our knowledge, no work has specifically investigated the performance of LLMsin natural language generation (NLG) tasks, a pivotal criterion for determining modelexcellence. Thus, this paper conducts a comprehensive evaluation of well-known andhigh-performing LLMs, namely ChatGPT, ChatGLM, T5-based models, LLaMA-basedmodels, and Pythia-based models, in the context of NLG tasks. We select English andChinese datasets encompassing Dialogue Generation and Text Summarization. More-over, we propose a common evaluation setting that incorporates input templates andpost-processing strategies. Our study reports both automatic results, accompanied by adetailed analysis.”

Open-domain multi-turn dialogue generation encounters the significant challenge of lacking various types of knowledge from diverse sources. Existing models typically focus on identifying specific types of dialogue knowledge and utilize corresponding datasets for training. However, this approach often leads to limited generalization capabilities and increased computational resource requirements. Recently, large language models (LLMs) have shown impressive performance on natural language processing tasks. To harness the knowledge storage of LLMs, we propose a framework named KnowEE that explores multi-source multi-type knowledge from LLMs by leveraging diverse datasets and then exploits the obtained knowledge for response generation. Our framework comprises two phases: First, we leverage five external datasets encompassing various types of knowledge to extract the most relevant samples to the dialogue context which are served as prompts to generate corresponding type of knowledge; Second, we inject the acquired knowledge into the ongoing dialogue context in fine-grained and coarse-grained manners, which is then fed into LLMs to generate the final dialogue response. Both automatic and manual evaluation results validate the effectiveness of our framework in exploring and exploiting multi-source multi-type knowledge to generate coherent, informative, and fluent responses.

“开放式自动故事生成通过输入故事的开头、大纲、主线等,得到具有一致性、连贯性和逻辑性的故事。现有的方法想要提升生成故事的质量,往往需要大量训练数据和更多参数的模型。针对以上问题,该文利用提示学习在零样本与少样本场景下的优势,同时使用外部常识推理知识,提出了一种故事生成方法。该方法将故事生成分为三个阶段:输入故事的开头,常识推理模型生成可能的事件;根据类型不同,将事件填入问题模板中,构建引导模型生成合理回答的问题;问答模型产生对应问题的答案,并选择困惑度最小的作为故事下文。重复上述过程,最终生成完整的故事。自动评测与人工评测指标表明,与基线模型相比,该文提出的方法能够生成更连贯、具体和合乎逻辑的故事。”