In the paper, we consider multilevel multitask analysis of cryptocurrency news using a fine-tuned Mistral 7B large language model with retrieval-augmented generation (RAG). On the first level of analytics, the fine-tuned model generates graph and text summaries with sentiment scores as well as JSON representations of summaries. Higher levels perform hierarchical stacking that consolidates sets of graph-based and text-based summaries as well as summaries of summaries into comprehensive reports. The combination of graph and text summaries provides complementary views of cryptocurrency news. The model is fine-tuned with 4-bit quantization using the PEFT/LoRA approach. The representation of cryptocurrency news as knowledge graph can essentially eliminate problems with large language model hallucinations. The obtained results demonstrate that the use of fine-tuned Mistral 7B LLM models for multilevel cryptocurrency news analysis can conduct informative qualitative and quantitative analytics, providing important insights.

Relation extraction enables the construction of structured knowledge for many downstream applications. While large language models (LLMs) have shown great promise in this domain, most existing methods concentrate on relation classification, which predicts the semantic relation type between a related entity pair. However, we observe that LLMs often struggle to reliably determine whether a relation exists, especially in cases involving complex sentence structures or intricate semantics, which leads to spurious predictions. Such hallucinations can introduce noisy edges in knowledge graphs, compromising the integrity of structured knowledge and downstream reliability. To address these challenges, we propose DEPTH, a framework that integrates Dependency-aware sEntence simPlification and Two-tiered Hierarchical refinement into the relation extraction pipeline. Given a sentence and its candidate entity pairs, DEPTH operates in two stages: (1) the Grounding module extracts relations for each pair by leveraging their shortest dependency path, distilling the sentence into a minimal yet coherent relational context that reduces syntactic noise while preserving key semantics; (2) the Refinement module aggregates all local predictions and revises them based on a holistic understanding of the sentence, correcting omissions and inconsistencies. We further introduce a causality-driven reward model that mitigates reward hacking by disentangling spurious correlations, enabling robust fine-tuning via reinforcement learning with human feedback. Experiments on six benchmarks demonstrate that DEPTH reduces the average hallucination rate to 7.0\% while achieving a 17.2\% improvement in average F1 score over state-of-the-art baselines.

Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation methods heavily rely on Multi-modal Large Language Models (MLLMs), particularly powerful commercial models like GPT-4o. While these models are highly effective, their substantial costs limit scalability in large-scale evaluations. Adopting open-source MLLMs is an alternative; however, their performance falls short due to significant limitations in processing multi-modal data compared to commercial MLLMs. To tackle these problems, we first propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset, where the complex evaluation task is decoupled into simpler sub-tasks, effectively reducing the learning complexity. Based on this dataset, we design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Furthermore, to reliably and comprehensively assess prior works and our proposed model, we manually annotate a meta-evaluation benchmark that includes chain-of-thought explanations alongside quality scores for generated images. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline, VIEScore, with over 4.6\% improvement in Spearman and Kendall correlations with human judgments.

Data annotation refers to the labeling or tagging of textual data with relevant information. A large body of works have reported positive results on leveraging LLMs as an alternative to human annotators. However, existing studies focus on classic NLP tasks, and the extent to which LLMs as data annotators perform in domains requiring expert knowledge remains underexplored. In this work, we investigate comprehensive approaches across three highly specialized domains and discuss practical suggestions from a cost-effectiveness perspective. To the best of our knowledge, we present the first systematic evaluation of LLMs as expert-level data annotators.

Compositional generalization is an important ability of language models and has many different manifestations. For data-to-text generation, previous research on this ability is limited to a single manifestation called Systematicity and lacks consideration of large language models (LLMs), which cannot fully cover practical application scenarios. In this work, we propose SPOR, a comprehensive and practical evaluation method for compositional generalization in data-to-text generation. SPOR includes four aspects of manifestations (Systematicity, Productivity, Order invariance, and Rule learnability) and allows high-quality evaluation without additional manual annotations based on existing datasets. We demonstrate SPOR on two different datasets and evaluate some existing language models including LLMs. We find that the models are deficient in various aspects of the evaluation and need further improvement. Our work shows the necessity for comprehensive research on different manifestations of compositional generalization in data-to-text generation and provides a framework for evaluation.

Generative Large language models (LLMs) have demonstrated remarkable capabilities for a wide range of applications, but reducing ungrounded or erroneous responses remains a major growth area. Unlike task-specific models, there lack an effective method to calibrate the confidence level of LLM responses to indicate potential errors and facilitate human-in-the-loop verification. An important source of calibration stems from expert-stipulated programmatic supervision, which is often available at low cost but has its own limitations such as noise and coverage. In this paper, we introduce a Pareto optimal self-supervision framework that can leverage available programmatic supervision to systematically calibrate LLM responses by producing a risk score for every LLM response, without any additional manual efforts. This is accomplished by learning a harmonizer model to align with LLM output as well as other weak supervision sources. The model assigns higher risk scores to more uncertain LLM responses and facilitate error correction. Experiments on standard relation extraction and classification tasks in biomedical and general domains demonstrate that the proposed risk score is highly correlated with the actual LLM error rate. By using a dynamic prompting strategy based on the risk score, we observed significant accuracy improvement for off-the-shelf LLMs, boosting GPT-3.5 results past state-of-the-art (SOTA) weak supervision model and GPT-4 results past SOTA supervised results on challenging evaluation datasets.

Context: Conflicts between software requirements bring uncertainties to product development. Some great approaches have been proposed to identify these conflicts. However, they usually require the software requirements represented with specific templates and/or depend on other external source which is often uneasy to build for lots of projects in practice. Objective: We aim to propose an approach Finer Semantic Analysis-based Requirements Conflict Detector (FSARC) to automatically detecting the conflicts between the given natural language functional requirements by analyzing their finer semantic compositions. Method: We build a harmonized semantic meta-model of functional requirements with the form of eight-tuple. Then we propose algorithms to automatically analyze the linguistic features of requirements and to annotate the semantic elements for their semantic model construction. And we define seven types of conflicts as long as their heuristic detecting rules on the ground of their text pattern and semantical dependency. Finally, we design and implement the algorithm for conflicts detection. Results: The experiment with four requirement datasets illustrates that the recall of FSARC is nearly 100% and the average precision is 83.88% on conflicts detection. Conclusion: We provide a useful tool for detecting the conflicts between natural language functional requirements to improve the quality of the final requirements set. Besides, our approach is capable of transforming the natural language functional requirements into eight semantic tuples, which is useful not only the detection of the conflicts between requirements but also some other tasks such as constructing the association between requirements and so on.