Natural Language Processing news and analysis on Web Pulse: 5561 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A new study from arXiv (2607.16790v1) directly compares cascaded and joint multi-task modeling for hierarchical offensive language detection, finding that a cascaded system achieves macro-F1 scores of 0.795, 0.716, and 0…
Researchers have introduced Shapley Context Pruning (SCP), a novel framework for context reranking in Retrieval-Augmented Generation (RAG) systems that applies cooperative game theory to attribute importance at the sente…
A new arXiv preprint introduces ColGraphRAG, a late-interaction evidence retrieval method for multimodal GraphRAG that replaces single-vector bi-encoder similarity with MaxSim-style multi-vector scoring for graph-linked …
The NOWJ team presents adaptive pipelines for all five tasks of the COLIEE 2026 competition, including legal case retrieval, entailment, statute law retrieval, textual entailment, and judgment prediction. Their approach …
Researchers propose RIMS, a three-stage preference optimization framework for small-scale language models in retrieval-augmented generation, which uses synthetic chain-of-thought preference data and a differentiable soft…
A new study from arXiv introduces Symbolic Augmentation, a training-time framework that generates label-preserving augmented data to fix a structural blind spot in neural fact-checkers: their accuracy on canonical-equiva…
A new study from dessertlab shows that fine-tuned mid-sized open LLMs can outperform GPT baselines in schema-constrained document-level event argument extraction on the MAVEN-ARG benchmark. The approach combines role-set…
Researchers propose DocOCR-Eval, an annotation-free framework for automatically evaluating and selecting OCR tools without ground-truth labels. The framework uses a three-stage correction and ranking strategy that aggreg…
A new study by Cory Massaro, published on arXiv, finds that LLM-generated text exhibits consistent statistical patterns in n-gram distributions that differ from human writing, revealing stylistic deficiencies. The analys…
Ricardo Figueroa, a solo developer, launched AI Assist, a $3 one-time meeting notes tool that runs locally in the browser with no bot joining calls, using users' own Anthropic and OpenAI API keys for LLM and transcriptio…
A developer built an autonomous AI physician assistant using the AutoGPT protocol, OpenAI API, and SerpApi to transform raw medical reports into actionable healthcare roadmaps. The agent uses a feedback loop to research …
Vidmoat, a new video editor built for AI agents, allows users to edit videos by giving plain-language commands to an integrated agent or connecting external agents like Claude Code and Cursor via the Model Context Protoc…
Researchers from Sorbonne Université and CNRS have developed the first reinforcement learning-based dialogue manager for simulated group motivational interviewing, using a discrete Soft-Actor-Critic policy to select ther…
A survey by Michelle Elizabeth, Gwénolé Lecorvé, Lina M. Rojas Barahona, and Magalie Ochs, presented at the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) in August 2026, finds that…
Yash Raj Singh presents CrossOracle, a production-deployed spoken dialogue system for real-time Hinglish voice interaction across eleven Expert Persona identities, achieving a mean TTS Real-Time Factor of 0.107 and a 100…
A study of 49 programmers interacting with GitHub Copilot to assess 148 HIPAA-derived Non-Functional Requirements against the iTrust codebase found that developers tend to agree with LLM assessments, but accuracy against…
Researchers from the Association for Computational Linguistics have developed a dialogue system for second language learning that dynamically adjusts utterance difficulty based on the learner's topic-specific proficiency…
ByteDance quietly upgraded its Seed 1.0 audio generation model with timestamp pinning for dialogue, allowing creators to lock spoken lines to exact timestamps instead of relying on the model's default pacing. The update …
Researchers at the Association for Computational Linguistics presented a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with a focus on human-AI and multi-agent collaboration. The …
Researchers Henry Gao and Jinho D. Choi have developed a task-oriented dialogue system that uses large language models with in-context prompting and unstructured conversational logs, eliminating the need for annotated da…