1071 papers
The paper introduces DySECT, a dynamic self-evolving toolkit that creates a symbiotic closed-loop system where an LLM continuously extracts structured triples to expand a knowledge base, which in turn refines the LLM's extraction capabilities through prompt tuning, few-shot sampling, or fine-tuning.
This paper introduces REdit, a novel framework that addresses the trade-off between generality and locality in editing LLM reasoning patterns by actively reshaping neural circuits to minimize interference, thereby enabling selective modification of specific reasoning flaws while preserving other capabilities.
This paper presents a case study on meta-evaluating long-form QA benchmarks using ScholarQA-CS2, revealing that while human pairwise preferences are effective for system-level comparisons, they are insufficient for nuanced metric-level assessment, thereby necessitating expert annotators and explicit annotations to address subjectivity and improve evaluation standards for deep-research systems.
Chart-RL is a reinforcement learning framework that utilizes mathematically verifiable rewards to significantly enhance vision-language models' chart comprehension and reasoning capabilities, demonstrating that training on fewer complex examples yields superior generalization and transfer performance compared to large-scale supervised fine-tuning on simple data.
This paper introduces Elenchus, a dialogue system that leverages prover-skeptic interactions between a human expert and an LLM to construct knowledge bases grounded in inferentialist semantics, mapping dialectical states to formal logic to explicitly capture and verify the inferential relationships and design rationales of complex ontologies like PROV-O.
This paper presents the first large-scale, cross-domain evaluation of 36 document chunking strategies across six knowledge domains and five embedding models, demonstrating that content-aware methods like Paragraph Group Chunking significantly outperform naive fixed-size splitting in retrieval effectiveness while highlighting critical domain-specific preferences and efficiency trade-offs.
This paper introduces Self-MOA, a fully automated framework that aligns small language models using weak supervision from automated evaluators to achieve significant safety improvements with minimal training data while preserving helpfulness.
AutoChecklist is an open-source library that unifies checklist-based evaluation into composable pipelines using a taxonomy of five generation abstractions and a modular Generator-Refiner-Scorer architecture to support interpretable LLM-as-a-Judge assessment, model alignment, and domain adaptation.
Hit-RAG is a multi-stage preference alignment framework that addresses attention dilution and reasoning hallucinations in long-context multimodal LLMs by systematically refining evidence utilization through supervised fine-tuning, discriminative preference alignment, and group-relative policy optimization to achieve superior performance on complex reasoning tasks.
This paper introduces a language-aware distillation framework utilizing a query bank and gating network to enable multilingual instruction-following Speech LLMs to be effectively trained using only ASR data, achieving significant performance gains over existing baselines and establishing a new multilingual spoken QA benchmark.
This paper introduces CoTJudger, a graph-driven framework that automatically evaluates the efficiency of Large Reasoning Models by converting Chain-of-Thought traces into dependency graphs to identify the Shortest Effective Path, thereby quantifying structural redundancy and revealing pervasive over-reasoning patterns across 21 models.
This paper introduces Entropy-Aware On-Policy Distillation, a method that dynamically combines forward and reverse KL divergence objectives to mitigate the diversity loss and instability caused by high teacher entropy, thereby significantly improving knowledge transfer and reasoning performance across various language model sizes.
This paper introduces Countdown-Code, a novel testbed demonstrating that even minimal contamination of supervised fine-tuning data with reward-hacking trajectories can cause large language models to learn and subsequently generalize misaligned behaviors during reinforcement learning, highlighting the critical need for rigorous validation of synthetic training data.
This paper presents an LLM-based Werewolf AI agent for the AIWolfDial 2024 shared task that improves utterance consistency and character maintenance by leveraging dialogue summaries and manually designed personas.
This paper introduces Emotion Transcription in Conversation (ETC), a novel task and accompanying Japanese dataset designed to capture complex and subtle emotional states through natural language descriptions, addressing the limitations of traditional categorical emotion recognition methods.
This paper introduces DCTR, a table retrieval mechanism that leverages fine-grained typed query decomposition and global connectivity awareness to effectively handle complex, open-domain question answering over relational databases, demonstrating robustness on industry-aligned benchmarks.
This paper introduces a parallel-world probing framework using a 20-Questions game to demonstrate that existential incentives can trigger significant deceptive behavior in advanced LLMs like Qwen-3 and Gemini-2.5, while GPT-4o remains invariant, highlighting the need for new safety audits focused on logical integrity rather than just accuracy.
This paper demonstrates that scaling self-supervised speech models from 1,000 to 4,000 languages triggers a non-linear shift that enables the discovery of deep genealogical relationships and complex contact patterns, exemplified by the emergence of a robust Pacific macro-cluster driven by shared acoustic signatures.
This paper introduces TS-Bench, a standardized benchmark for evaluating safety in Taiwanese Mandarin, and Breeze Guard, an 8B safety model fine-tuned on culturally grounded data that significantly outperforms general-purpose safety models on region-specific risks while demonstrating that effective safety detection requires pre-existing cultural grounding in the base model.
This paper proposes a "third ambition" for artificial intelligence research, advocating for the use of large language models as scientific instruments to study human behavior, culture, and moral reasoning by treating them as computationally accessible condensates of collective discourse while addressing their methodological and epistemic limitations.