arXiv:2604.07042v1 Announce Type: new Abstract: Most research in planning focuses on generating a plan to achieve a desired set of goals. However, a goal specification can also be used to encode a property that should never hold, allowing a planner to identify a trace that would reach a flawed state. In such cases, the objective […]
Probing 3D Chromatin Structure Awareness in Evo2 DNA Language Model
arXiv:2604.07196v1 Announce Type: new Abstract: DNA language models like Evo2 now fit million-token contexts large enough to cover entire TADs, yet whether they learn 3D chromatin structure, a key regulatory layer acting atop primary sequence, remains untested and questionable, given that Evo2’s training data includes prokaryotes lacking this structure. We probed Evo2-7B on TAD boundaries […]
Knowledge Graphs Generation from Cultural Heritage Texts: Combining LLMs and Ontological Engineering for Scholarly Debates
arXiv:2511.10354v1 Announce Type: cross Abstract: Cultural Heritage texts contain rich knowledge that is difficult to query systematically due to the challenges of converting unstructured discourse into structured Knowledge Graphs (KGs). This paper introduces ATR4CH (Adaptive Text-to-RDF for Cultural Heritage), a systematic five-step methodology for Large Language Model-based Knowledge Extraction from Cultural Heritage documents. We validate […]
Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA
arXiv:2604.06173v1 Announce Type: cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory domains, relevant evidence is distributed across hierarchically linked documents, creating a statutory retrieval gap where conventional retrievers fail and models often hallucinate under incomplete context. We introduce SearchFireSafety, a structure- and […]
A Goal-Oriented Chatbot for Engaging the Elderly Through Family Photo Conversations
arXiv:2604.06184v1 Announce Type: cross Abstract: We propose a personalized chatbot designed for elderly individuals. The chatbot initiates discussions based on family photos, encouraging users to interact naturally. During these interactions, it generates W questions (who, where, when, and what) to stimulate cognitive function, followed by an open-ended question to promote positive reminiscence. This approach is […]
Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment
arXiv:2604.06191v1 Announce Type: cross Abstract: Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a […]
Consistency-Guided Decoding with Proof-Driven Disambiguation for Three-Way Logical Question Answering
arXiv:2604.06196v1 Announce Type: cross Abstract: Three-way logical question answering (QA) assigns $True/False/Unknown$ to a hypothesis $H$ given a premise set $S$. While modern large language models (LLMs) can be accurate on isolated examples, we identify two recurring failure modes in 3-way logic QA: (i) negation inconsistency, where answers to $H$ and $neg H$ violate the […]
Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models
arXiv:2604.06201v1 Announce Type: cross Abstract: While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require understanding distributional information, such as population-level trends and preferences expressed across collections of text. We introduce Text2DistBench, a reading comprehension benchmark for evaluating LLMs’ ability to […]
Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation
arXiv:2604.06205v1 Announce Type: cross Abstract: The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. While large language models (LLMs) are effective, their high computational cost and latency present significant challenges for scalable deployment. To address this, we introduce Tool-MCoT, a small language […]
A-MBER: Affective Memory Benchmark for Emotion Recognition
arXiv:2604.07017v1 Announce Type: new Abstract: AI assistants that interact with users over time need to interpret the user’s current emotional state in order to respond appropriately and personally. However, this capability remains insufficiently evaluated. Existing emotion datasets mainly assess local or instantaneous affect, while long-term memory benchmarks focus largely on factual recall, temporal consistency, or […]
EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration
arXiv:2604.07070v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, their potential for purpose-driven exploration in dynamic geo-spatial environments remains under-investigated. Existing Geo-Spatial Question Answering (GSQA) benchmarks predominantly focus on static retrieval, failing to capture the complexity of real-world planning that involves dynamic user locations and compound constraints. To bridge this […]
Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
arXiv:2604.07165v1 Announce Type: new Abstract: Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimization treat sampled trajectories as independent chains, assigning uniform credit to all steps in each chain and ignoring the existence of critical steps that may disproportionally impact […]