The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation

The extraction of information about traffic accidents from legal documents is crucial for quantifying insurance company costs. Extracting entities such as percentages of physical and/or psychological disability and the involved compensation amounts is a challenging process, even for experts, due to the subtle arguments and reasoning in the court decision. A two-step procedure is proposed: first, segmenting the document identifying the most relevant segments, and then extracting the entities. For text segmentation, two methodologies are compared: a classic method based on regular expressions and a second approach that divides the document into blocks of n-tokens, which are then vectorized using multilingual models for semantic searches (text-embedding-ada-002/MiniLM-L12-v2 ). Subsequently, large language models (LLaMA-2 7b, 70b, LLaMA-3 8b, and GPT-4 Turbo) are applied with prompting to the selected segments for entity extraction. For the LLaMA models, fine-tuning is performed using LoRA. LLaMA-2 7b, even with zero temperature, shows a significant number of hallucinations in extractions which are an important contention point for named entity extraction. This work shows that these hallucinations are substantially reduced after finetuning the model. The performance of the methodology based on segment vectorization and subsequent use of LLMs significantly surpasses the classic method which achieves an accuracy of 39.5%. Among open-source models, LLaMA-2 70B with finetuning achieves the highest accuracy 79.4%, surpassing its base version 61.7%. Notably, the base LLaMA-3 8B model already performs comparably to the finetuned LLaMA-2 70B model, achieving 76.6%, highlighting the rapid progress in model development. Meanwhile, GPT-4 Turbo achieves the highest accuracy at 86.1%.

Decompositional Reasoning for Graph Retrieval with Large Language Models

Large Language Models (LLMs) excel at many NLP tasks, but struggle with multi-hop reasoning and factual consistency, limiting their effectiveness on knowledge-intensive tasks like complex question answering (QA). Linking Knowledge Graphs (KG) and LLMs has shown promising results, but LLMs generally lack the ability to reason efficiently over graph-structured information. To tackle this problem, we propose a novel retrieval approach that integrates textual knowledge graphs into the LLM reasoning process via query decomposition. Our method decomposes complex questions into sub-questions, retrieves relevant textual subgraphs, and composes a question-specific knowledge graph to guide answer generation. For that, we use a weighted similarity function that focuses on both the complex question and the generated subquestions to extract a relevant subgraph, which allows efficient and precise retrieval for complex questions and improves the performance of LLMs on multi-hop QA tasks. This structured reasoning pipeline enhances factual grounding and interpretability while leveraging the generative strengths of LLMs. We evaluate our method on standard multi-hop QA benchmarks and show that it achieves comparable or superior performance to competitive existing methods, using smaller models and fewer LLM calls.

Chaining Event Spans for Temporal Relation Grounding

Accurately understanding temporal relations between events is a critical building block of diverse tasks, such as temporal reading comprehension (TRC) and relation extraction (TRE). For example in TRC, we need to understand the temporal semantic differences between the following two questions that are lexically near-identical: "What finished right before the decision?" or "What finished right after the decision?". To discern the two questions, existing solutions have relied on answer overlaps as a proxy label to contrast similar and dissimilar questions. However, we claim that answer overlap can lead to unreliable results, due to spurious overlaps of two dissimilar questions with coincidentally identical answers. To address the issue, we propose a novel approach that elicits proper reasoning behaviors through a module for predicting time spans of events. We introduce the Timeline Reasoning Network (TRN) operating in a two-step inductive reasoning process: In the first step model initially answers each question with semantic and syntactic information. The next step chains multiple questions on the same event to predict a timeline, which is then used to ground the answers. Results on the TORQUE and TB-dense, TRC and TRE tasks respectively, demonstrate that TRN outperforms previous methods by effectively resolving the spurious overlaps using the predicted timeline.

Cross-Modal Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition

LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent point cloud density, induced by ego-motion dynamics and environmental disturbances during repeated traversals, leads to descriptor instability, and (2) Representation fragility stems from reliance on single-level geometric abstractions that lack discriminative power in structurally complex scenarios. To address these limitations, we propose a novel framework that redefines 3D place recognition through density-agnostic geometric reasoning. Specifically, we introduce an implicit 3D representation based on elastic points, which is immune to the interference of original scene point cloud density and achieves the characteristic of uniform distribution. Subsequently, we derive the occupancy grid and normal vector information of the scene from this implicit representation. Finally, with the aid of these two types of information, we obtain descriptors that fuse geometric information from both bird's-eye view (capturing macro-level spatial layouts) and 3D segment (encoding micro-scale surface geometries) perspectives. We conducted extensive experiments on numerous datasets (KITTI, KITTI-360, MulRan, NCLT) across diverse environments. The experimental results demonstrate that our method achieves state-of-the-art performance. Moreover, our approach strikes an optimal balance between accuracy, runtime, and memory optimization for historical maps, showcasing excellent Resilient and scalability. Our code will be open-sourced in the future.

ViT-NeBLa: A Hybrid Vision Transformer and Neural Beer-Lambert Framework for Single-View 3D Reconstruction of Oral Anatomy from Panoramic Radiographs

Dental diagnosis relies on two primary imaging modalities: panoramic radiographs (PX) providing 2D oral cavity representations, and Cone-Beam Computed Tomography (CBCT) offering detailed 3D anatomical information. While PX images are cost-effective and accessible, their lack of depth information limits diagnostic accuracy. CBCT addresses this but presents drawbacks including higher costs, increased radiation exposure, and limited accessibility. Existing reconstruction models further complicate the process by requiring CBCT flattening or prior dental arch information, often unavailable clinically. We introduce ViT-NeBLa, a vision transformer-based Neural Beer-Lambert model enabling accurate 3D reconstruction directly from single PX. Our key innovations include: (1) enhancing the NeBLa framework with Vision Transformers for improved reconstruction capabilities without requiring CBCT flattening or prior dental arch information, (2) implementing a novel horseshoe-shaped point sampling strategy with non-intersecting rays that eliminates intermediate density aggregation required by existing models due to intersecting rays, reducing sampling point computations by $52 \%$, (3) replacing CNN-based U-Net with a hybrid ViT-CNN architecture for superior global and local feature extraction, and (4) implementing learnable hash positional encoding for better higher-dimensional representation of 3D sample points compared to existing Fourier-based dense positional encoding. Experiments demonstrate that ViT-NeBLa significantly outperforms prior state-of-the-art methods both quantitatively and qualitatively, offering a cost-effective, radiation-efficient alternative for enhanced dental diagnostics.

CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following

Recent advances in audio-text large language models (LLMs) have opened new possibilities for music understanding and generation. However, existing benchmarks are limited in scope, often relying on simplified tasks or multi-choice evaluations that fail to reflect the complexity of real-world music analysis. We reinterpret a broad range of traditional MIR annotations as instruction-following formats and introduce CMI-Bench, a comprehensive music instruction following benchmark designed to evaluate audio-text LLMs on a diverse set of music information retrieval (MIR) tasks. These include genre classification, emotion regression, emotion tagging, instrument classification, pitch estimation, key detection, lyrics transcription, melody extraction, vocal technique recognition, instrument performance technique detection, music tagging, music captioning, and (down)beat tracking: reflecting core challenges in MIR research. Unlike previous benchmarks, CMI-Bench adopts standardized evaluation metrics consistent with previous state-of-the-art MIR models, ensuring direct comparability with supervised approaches. We provide an evaluation toolkit supporting all open-source audio-textual LLMs, including LTU, Qwen-audio, SALMONN, MusiLingo, etc. Experiment results reveal significant performance gaps between LLMs and supervised models, along with their culture, chronological and gender bias, highlighting the potential and limitations of current models in addressing MIR tasks. CMI-Bench establishes a unified foundation for evaluating music instruction following, driving progress in music-aware LLMs.

Real-Time Per-Garment Virtual Try-On with Temporal Consistency for Loose-Fitting Garments

Per-garment virtual try-on methods collect garment-specific datasets and train networks tailored to each garment to achieve superior results. However, these approaches often struggle with loose-fitting garments due to two key limitations: (1) They rely on human body semantic maps to align garments with the body, but these maps become unreliable when body contours are obscured by loose-fitting garments, resulting in degraded outcomes; (2) They train garment synthesis networks on a per-frame basis without utilizing temporal information, leading to noticeable jittering artifacts. To address these challenges, we propose a two-stage approach for robust semantic map estimation. First, we extract a garment-invariant representation from the raw input image. This representation is then passed through an auxiliary network to estimate the semantic map. This enhances the robustness of semantic map estimation under loose-fitting garments during garment-specific dataset generation. Furthermore, we introduce a recurrent garment synthesis framework that incorporates temporal dependencies to improve frame-to-frame coherence while maintaining real-time performance. We conducted qualitative and quantitative evaluations to demonstrate that our method outperforms existing approaches in both image quality and temporal coherence. Ablation studies further validate the effectiveness of the garment-invariant representation and the recurrent synthesis framework.

SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation

Text-to-SQL enables non-experts to retrieve data from databases by converting natural language queries into SQL. However, state-of-the-art text-to-SQL studies rely on the BIRD dataset, which assumes that evidence is provided along with questions. Although BIRD facilitates research advancements, it assumes that users have expertise and domain knowledge, contradicting the fundamental goal of text-to-SQL. In addition, human-generated evidence in BIRD contains defects, including missing or erroneous evidence, which affects model performance. To address this issue, we propose SEED (System for Evidence Extraction and Domain knowledge generation), an approach that automatically generates evidence to improve performance and practical usability in real-world scenarios. SEED systematically analyzes database schema, description files, and values to extract relevant information. We evaluated SEED on BIRD and Spider, demonstrating that it significantly improves SQL generation accuracy in the no-evidence scenario, and in some cases, even outperforms the setting where BIRD evidence is provided. Our results highlight that SEED-generated evidence not only bridges the gap between research and real-world deployment but also improves the adaptability and robustness of text-to-SQL models. Our code is available at https://github.com/felix01189/SEED

MF2Summ: Multimodal Fusion for Video Summarization with Temporal Alignment

The rapid proliferation of online video content necessitates effective video summarization techniques. Traditional methods, often relying on a single modality (typically visual), struggle to capture the full semantic richness of videos. This paper introduces MF2Summ, a novel video summarization model based on multimodal content understanding, integrating both visual and auditory information. MF2Summ employs a five-stage process: feature extraction, cross-modal attention interaction, feature fusion, segment prediction, and key shot selection. Visual features are extracted using a pre-trained GoogLeNet model, while auditory features are derived using SoundNet. The core of our fusion mechanism involves a cross-modal Transformer and an alignment-guided self-attention Transformer, designed to effectively model inter-modal dependencies and temporal correspondences. Segment importance, location, and center-ness are predicted, followed by key shot selection using Non-Maximum Suppression (NMS) and the Kernel Temporal Segmentation (KTS) algorithm. Experimental results on the SumMe and TVSum datasets demonstrate that MF2Summ achieves competitive performance, notably improving F1-scores by 1.9\% and 0.6\% respectively over the DSNet model, and performing favorably against other state-of-the-art methods.

CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility Simulation

Human mobility simulation plays a crucial role in various real-world applications. Recently, to address the limitations of traditional data-driven approaches, researchers have explored leveraging the commonsense knowledge and reasoning capabilities of large language models (LLMs) to accelerate human mobility simulation. However, these methods suffer from several critical shortcomings, including inadequate modeling of urban spaces and poor integration with both individual mobility patterns and collective mobility distributions. To address these challenges, we propose \textbf{C}ityGPT-Powered \textbf{A}gentic framework for \textbf{M}obility \textbf{S}imulation (\textbf{CAMS}), an agentic framework that leverages the language based urban foundation model to simulate human mobility in urban space. \textbf{CAMS} comprises three core modules, including MobExtractor to extract template mobility patterns and synthesize new ones based on user profiles, GeoGenerator to generate anchor points considering collective knowledge and generate candidate urban geospatial knowledge using an enhanced version of CityGPT, TrajEnhancer to retrieve spatial knowledge based on mobility patterns and generate trajectories with real trajectory preference alignment via DPO. Experiments on real-world datasets show that \textbf{CAMS} achieves superior performance without relying on externally provided geospatial information. Moreover, by holistically modeling both individual mobility patterns and collective mobility constraints, \textbf{CAMS} generates more realistic and plausible trajectories. In general, \textbf{CAMS} establishes a new paradigm that integrates the agentic framework with urban-knowledgeable LLMs for human mobility simulation.