Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of using human-labeled data. We introduce FineSumFact, a large-scale dataset containing fine-grained factual feedback on summaries. We employ 10 distinct LLMs for diverse summary generation and Llama-3-70B-Instruct for feedback. We utilize this dataset to fine-tune the lightweight open-source model Llama-3-8B-Instruct, optimizing resource efficiency while maintaining high performance. Our experimental results reveal that the model trained on extensive LLM-generated datasets surpasses that trained on smaller human-annotated datasets when evaluated using human-generated test sets. Fine-tuning fact verification models with LLM feedback can be more effective and cost-efficient than using human feedback. The dataset is available at https://github.com/DISL-Lab/FineSumFact.

Small Language Models (SLMs) are attracting attention due to the high computational demands and privacy concerns of Large Language Models (LLMs). Some studies fine-tune SLMs using Chains of Thought (CoT) data distilled from LLMs, aiming to enhance their reasoning ability. Furthermore, Some CoT distillation methods introduce external symbolic knowledge into the generation process to improve the limited knowledge memory, reasoning ability and out-of-domain (OOD) generalization of SLMs. However, the introduction of symbolic knowledge increases computational overhead and introduces potential noise. In this paper, we introduce $\textit{SKIntern}$, an innovative approach that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process, guided by a predefined linear decay schedule under curriculum learning. By efficiently internalizing knowledge, $\textit{SKIntern}$ reduces computational overhead and speeds up the reasoning process by focusing solely on the question during inference. It outperforms state-of-the-art baselines by over 5\%, while reducing inference costs (measured in FLOPs) by up to $4\times$ across a wide range of SLMs in both in-domain (ID) and out-of-domain (OOD) tasks. Our code will be available at \url{https://github.com/Xnhyacinth/SKIntern}.

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this issue, we propose a method named \textbf{IRR} (\textbf{I}dentify, \textbf{R}emove, and \textbf{R}ecalibrate for Safety Realignment) that performs safety realignment for LLMs. The core of IRR is to identify and remove unsafe delta parameters from the fine-tuned models, while recalibrating the retained ones. We evaluate the effectiveness of IRR across various datasets, including both full fine-tuning and LoRA methods. Our results demonstrate that IRR significantly enhances the safety performance of fine-tuned models on safety benchmarks, such as harmful queries and jailbreak attacks, while maintaining their performance on downstream tasks. The source code is available at: \url{https://anonymous.4open.science/r/IRR-BD4F}.

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in large language models (LLMs). We observe that CoT shares significant similarities with self-training in terms of their learning processes. Motivated by these parallels, this paper explores the underlying relationship between CoT and self-training, demonstrating how insights from self-training can enhance CoT performance. Specifically, our study first reveals that CoT, like self-training, follows the principle of semantic entropy minimization. Leveraging this insight, we propose a novel CoT framework that incorporates two key components: (i) a task-specific prompt module designed to guide LLMs in generating high-quality initial reasoning processes, and (ii) an adaptive reasoning iteration module for progressively refining the reasoning process.

Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into semantic triplets for accurate Scene Graph Generation (SGG) is highly challenging due to the fluctuating spatio-temporal complexity. Inspired by the reasoning capabilities of Large Language Models (LLMs), we propose SceneLLM, a novel framework that leverages LLMs as powerful scene analyzers for dynamic SGG. Our framework introduces a Video-to-Language (V2L) mapping module that transforms video frames into linguistic signals (scene tokens), making the input more comprehensible for LLMs. To better encode spatial information, we devise a Spatial Information Aggregation (SIA) scheme, inspired by the structure of Chinese characters, which encodes spatial data into tokens. Using Optimal Transport (OT), we generate an implicit language signal from the frame-level token sequence that captures the video's spatio-temporal information. To further improve the LLM's ability to process this implicit linguistic input, we apply Low-Rank Adaptation (LoRA) to fine-tune the model. Finally, we use a transformer-based SGG predictor to decode the LLM's reasoning and predict semantic triplets. Our method achieves state-of-the-art results on the Action Genome (AG) benchmark, and extensive experiments show the effectiveness of SceneLLM in understanding and generating accurate dynamic scene graphs.

This study explores fine-tuning multilingual ASR (Automatic Speech Recognition) models, specifically OpenAI's Whisper-Tiny, to improve performance in Japanese. While multilingual models like Whisper offer versatility, they often lack precision in specific languages. Conversely, monolingual models like ReazonSpeech excel in language-specific tasks but are less adaptable. Using Japanese-specific datasets and Low-Rank Adaptation (LoRA) along with end-to-end (E2E) training, we fine-tuned Whisper-Tiny to bridge this gap. Our results show that fine-tuning reduced Whisper-Tiny's Character Error Rate (CER) from 32.7 to 20.8 with LoRA and to 14.7 with end-to-end fine-tuning, surpassing Whisper-Base's CER of 20.2. However, challenges with domain-specific terms remain, highlighting the need for specialized datasets. These findings demonstrate that fine-tuning multilingual models can achieve strong language-specific performance while retaining their flexibility. This approach provides a scalable solution for improving ASR in resource-constrained environments and languages with complex writing systems like Japanese.

Human-Centric NLP often claims to prioritise human needs and values, yet many implementations reveal an underlying AI-centric focus. Through an analysis of case studies in language modelling, behavioural testing, and multi-modal alignment, this study identifies a significant gap between the ideas of human-centricity and actual practices. Key issues include misalignment with human-centred design principles, the reduction of human factors to mere benchmarks, and insufficient consideration of real-world impacts. The discussion explores whether Human-Centric NLP embodies true human-centred design, emphasising the need for interdisciplinary collaboration and ethical considerations. The paper advocates for a redefinition of Human-Centric NLP, urging a broader focus on real-world utility and societal implications to ensure that language technologies genuinely serve and empower users.

The integration of documents generated by LLMs themselves (Self-Docs) alongside retrieved documents has emerged as a promising strategy for retrieval-augmented generation systems. However, previous research primarily focuses on optimizing the use of Self-Docs, with their inherent properties remaining underexplored. To bridge this gap, we first investigate the overall effectiveness of Self-Docs, identifying key factors that shape their contribution to RAG performance (RQ1). Building on these insights, we develop a taxonomy grounded in Systemic Functional Linguistics to compare the influence of various Self-Docs categories (RQ2) and explore strategies for combining them with external sources (RQ3). Our findings reveal which types of Self-Docs are most beneficial and offer practical guidelines for leveraging them to achieve significant improvements in knowledge-intensive question answering tasks.

We conducted three experiments to investigate how large language models (LLMs) evaluate posterior probabilities. Our results reveal the coexistence of two modes in posterior judgment among state-of-the-art models: a normative mode, which adheres to Bayes' rule, and a representative-based mode, which relies on similarity -- paralleling human System 1 and System 2 thinking. Additionally, we observed that LLMs struggle to recall base rate information from their memory, and developing prompt engineering strategies to mitigate representative-based judgment may be challenging. We further conjecture that the dual modes of judgment may be a result of the contrastive loss function employed in reinforcement learning from human feedback. Our findings underscore the potential direction for reducing cognitive biases in LLMs and the necessity for cautious deployment of LLMs in critical areas. The remarkable advancements in large language models (LLMs) have ushered in a new era where these models rival human expertise across domains like academia, law, medicine, and finance [4, 12, 13, 22-24]. In this study, we explore how LLMs judge this posterior probability. A higher similarity corresponds to a higher assessed posterior probability. This study comprises three experiments with progressively stricter conditions, reducing the information available for posterior likelihood assessment. The structured test provides all information needed for normative judgment, the semi-structured test omits the diagnosticity of evidence, and the unstructured test requires LLMs to recall all components of Bayes' rule. Results reveal that LLMs' judgments shift from f Representativeness can be constructed through typicality or prototypicality. Typicality describes the common or average case of the class, whereas prototypicality embodies the most idealized and iconic version of the class. For instance, a typical example of a physicist is a smart man who likes math and physics, while a prototypical example of a physicist is Stephen Hawking. This study moves beyond bias detection to investigate the basis upon which LLMs assess probabilities. This has important practical implications for the integration of LLMs into various critical fields.

The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex and realistic scenarios. However, EQA in real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration and response, bringing challenges especially for language beginners and non-expert users. To address this, we introduce a NoisyEQA benchmark designed to evaluate an agent's ability to recognize and correct noisy questions. This benchmark introduces four common types of noise found in real-world applications: Latent Hallucination Noise, Memory Noise, Perception Noise, and Semantic Noise generated through an automated dataset creation framework. Additionally, we also propose a 'Self-Correction' prompting mechanism and a new evaluation metric to enhance and measure both noise detection capability and answer quality. Our comprehensive evaluation reveals that current EQA agents often struggle to detect noise in questions, leading to responses that frequently contain erroneous information. Through our Self-Correct Prompting mechanism, we can effectively improve the accuracy of agent answers.