iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Home ›› Topics ›› nlp

Topic

nlp

38 stories
Creating Multilingual Mental Health Datasets: Study Reveals Limits of Persona-Based Localization via Nationality and Language Technology
Artificial Intelligence #mental health#multilingual

Creating Multilingual Mental Health Datasets: Study Reveals Limits of Persona-Based Localization via Nationality and Language

A new arxiv paper investigates whether persona-based methods can generate multilingual mental health dialogue datasets by modifying nationality and language. The study found that just adding these parameters introduces clinical inconsistencies across languages, and LLM judge models exhibit inaccuracies in assessing depression severity in non-English texts, highlighting the need for culturally responsive data generation.

Jul 8, 2026 1 source
FineREX Boosts Knowledge Graph Quality by 31% in Human Smuggling Document Analysis Technology
Artificial Intelligence #finetuning#ner

FineREX Boosts Knowledge Graph Quality by 31% in Human Smuggling Document Analysis

Researchers introduce FineREX, a fine-tuned NER-RE pipeline for knowledge graph construction from unstructured legal documents. Compared to a larger general-purpose LLM baseline, FineREX achieves absolute improvements of 15.50% in entity F1 and 31.46% in relation F1, reduces legal noise by nearly half, and cuts processing time by 50%.

Jul 8, 2026 1 source
CREDENCE Framework Improves Automated Fact-Checking with Semantic Metrics and Convergence Analysis Technology
Artificial Intelligence #ai#artificial intelligence

CREDENCE Framework Improves Automated Fact-Checking with Semantic Metrics and Convergence Analysis

The CREDENCE framework addresses key shortcomings in automated fact-checking by replacing Jaccard overlap metrics with Semantic-F1, a cosine similarity measure that improves accuracy by 15-32 percentage points. It also provides formal convergence theorems for repair pipelines and benchmarks across social media, encyclopedic, and news domains.

Jul 8, 2026 1 source
Toten Framework Outperforms Statistical Tokenization for Physical Quantities in Brazilian Portuguese Technical Texts Technology
Artificial Intelligence #tokenization#ontology

Toten Framework Outperforms Statistical Tokenization for Physical Quantities in Brazilian Portuguese Technical Texts

Researchers present Toten, a framework that replaces statistical tokenization with ontology-based classification for physical quantities and technical notation in Brazilian Portuguese. The system leverages external oracles and achieves higher ontological atomicity and numerical reconstruction compared to state-of-the-art baselines.

Jul 8, 2026 1 source
DeFrame: New Technique Debiases LLMs Against Subtle Framing Effects Technology
Artificial Intelligence #debiasing#llms

DeFrame: New Technique Debiases LLMs Against Subtle Framing Effects

Researchers at KAIST have identified framing disparity as an underexplored source of hidden bias in large language models (LLMs). Their proposed DeFrame method encourages consistent responses across semantically equivalent prompts, reducing overall bias and improving robustness against framing effects. The work has implications for enterprise AI deployments where fairness across demographics is critical.

Jun 21, 2026 1 source
Prompt Injection Attacks on LLM-Based Grading Systems Pose Security Risks for Enterprise AI Technology
Artificial Intelligence #prompt injection#llm

Prompt Injection Attacks on LLM-Based Grading Systems Pose Security Risks for Enterprise AI

A study by researchers at arXiv explores prompt injection attacks on large language model-based automatic grading systems, finding that current systems remain highly vulnerable to manipulation that could artificially inflate scores. The findings raise awareness of security threats in educational AI and serve as a warning for enterprise LLM deployments.

Jun 20, 2026 1 source
Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech Technology
Artificial Intelligence #code-switching#asr

Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech

A new code-mixing guided preference-learning framework improves code-switching automatic speech recognition (ASR) by steering synthetic speech generation toward better language-boundary consistency. Fine-tuning Whisper Large with this approach reduced Mixed Error Rate (MER) from 12.1% to 8.9% on the DevMAN set and from 17.8% to 14.2% on the DevSGE set of the SEAME Mandarin-English conversational corpus.

Jun 20, 2026 1 source
Large Language Models Can Read Compressed Text That Humans Cannot, Researchers Find Technology
Artificial Intelligence #large language models#artificial intelligence

Large Language Models Can Read Compressed Text That Humans Cannot, Researchers Find

A new research paper introduces BabelTele, a compact, non-human-readable text format that large language models can still interpret with high semantic fidelity. The approach compresses text to 27.9% of its original length while preserving 99.5% of meaning, potentially reducing context overhead and costs in enterprise AI deployments.

Jun 20, 2026 1 source
G2Rec Framework Structures and Tokenizes User Interests for Generative Recommendation Technology
Artificial Intelligence #ai#generative ai

G2Rec Framework Structures and Tokenizes User Interests for Generative Recommendation

The G2Rec framework, proposed by researchers, addresses limitations in generative recommendation by unifying holistic graph-based user co-engagement modeling with semantic tokenization. It enables scalable, accurate user interest modeling without requiring ground-truth interests, and has demonstrated superiority through online deployment and experiments on public datasets.

Jun 20, 2026 1 source
New Method LUCID Detects Hallucinations in LLM-Based Knowledge Graph Reasoning Technology
Artificial Intelligence #large language models#llms

New Method LUCID Detects Hallucinations in LLM-Based Knowledge Graph Reasoning

Researchers introduce LUCID, the first hallucination detection method designed for large language model-based knowledge graph reasoning. By jointly leveraging attention scores, KG semantics, and structural information via a graph neural network, LUCID achieves state-of-the-art performance across nine datasets compared to 15 baselines. The method addresses a critical gap where existing detection techniques overlook structural information in knowledge graphs.

Jun 20, 2026 2 sources
Before the Labels: How Dataset Construction Biases Suicidality Detection in Clinical Text Technology
Artificial Intelligence #dataset construction#suicidality detection

Before the Labels: How Dataset Construction Biases Suicidality Detection in Clinical Text

A new paper from arXiv argues that clinical NLP datasets built from electronic health records encode specific operationalizations of suicidality, shaped by governance constraints, ICD-based cohort selection, and annotation practices. The authors demonstrate that identical labels can subsume heterogeneous clinical framings, raising concerns for AI-driven healthcare decisions.

Jun 20, 2026 1 source
FAPO Framework Lets Claude Code Autonomously Optimize Multi-Step LLM Pipelines, Beats Baseline by 14.1 Points Technology
Artificial Intelligence #fapo#llm

FAPO Framework Lets Claude Code Autonomously Optimize Multi-Step LLM Pipelines, Beats Baseline by 14.1 Points

Researchers introduced FAPO, a framework that lets Claude Code autonomously optimize multi-step LLM pipelines by evaluating intermediate steps, diagnosing failures, and making scoped changes. Across six benchmarks and three task models, FAPO beat the baseline GEPA in 15 of 18 comparisons, with a mean gain of +14.1 percentage points.

Jun 20, 2026 1 source
Diffusion Language Models Show Promise but Demand Careful Inference Tuning, Study Finds Technology
Artificial Intelligence #diffusion#language models

Diffusion Language Models Show Promise but Demand Careful Inference Tuning, Study Finds

A new systematic study from researchers analyzes eight state-of-the-art Diffusion Language Models (DLMs) across eight benchmarks covering reasoning, coding, translation, and more. The research highlights how inference-time choices like denoising steps and context length create trade-offs between generation quality and computational efficiency, offering guidance for enterprise deployment.

Jun 20, 2026 1 source
S-SPPO: Semantic Calibration Boosts LLM Preference Alignment Without Human Data Technology
Artificial Intelligence #artificial intelligence#machine learning

S-SPPO: Semantic Calibration Boosts LLM Preference Alignment Without Human Data

S-SPPO, a dual-space semantic calibration framework, fixes instability in Self-Play Preference Optimization (SPPO) for large language models. By annealing win targets and enforcing geometric diversity, it achieves superior alignment results on AlpacaEval 2.0 without extra human preferences.

Jun 17, 2026 1 source
SAMark Watermarking Breaks Paraphrase Robustness Barrier for AI-Generated Text Technology
Artificial Intelligence #watermarking#text watermarking

SAMark Watermarking Breaks Paraphrase Robustness Barrier for AI-Generated Text

Researchers propose SAMark, a self-anchored text watermarking framework that achieves up to 90.2% true positive rate under paragraph-level paraphrasing attacks, outperforming the strongest prior baseline by more than 30% on average. The method breaks the robustness-quality trade-off by using multi-channel hyperbolic scoring and diversity-aware filtering.

Jun 17, 2026 1 source
New Hybrid Neuro-Symbolic Framework Achieves 78.1% Accuracy in Irony Detection Without Fine-Tuning Technology
Artificial Intelligence #ai#nlp

New Hybrid Neuro-Symbolic Framework Achieves 78.1% Accuracy in Irony Detection Without Fine-Tuning

Researchers propose the Robust Dual-Signal (RDS) Fusion framework, a hybrid neuro-symbolic architecture for irony detection in social media texts. Evaluated on TweetEval and iSarcasm datasets, RDS achieves 78.1% accuracy and a Macro F1 of 0.777, matching fine-tuned BERTweet without supervised fine-tuning.

Jun 17, 2026 1 source
New Legal QA Benchmark Exposes Hallucination Risks in Statute-Centric AI Retrieval Technology
Artificial Intelligence #legal qa#statute retrieval

New Legal QA Benchmark Exposes Hallucination Risks in Statute-Centric AI Retrieval

Researchers have introduced SearchFireSafety, a benchmark for statute-centric legal QA that evaluates hierarchical retrieval and safety. The study found that while graph-guided retrieval improves performance, domain-adapted large language models are more likely to hallucinate when key statutory evidence is missing, highlighting a critical safety trade-off.

Jun 17, 2026 1 source
Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling Technology
Artificial Intelligence #knowledge graphs#foundation models

Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling

Researchers propose KMAS, an adaptive negative sampling approach that enhances knowledge graph foundation models (KGFMs) by generating hard negative triples from relation embeddings. The method dynamically adjusts the ratio of hard negatives during training, improving performance across 44 datasets without significant extra time or memory.

Jun 16, 2026 2 sources
New Framework TRACED Evaluates LLM Reasoning Using Geometric Stability and Progress Technology
Artificial Intelligence #llms#reasoning

New Framework TRACED Evaluates LLM Reasoning Using Geometric Stability and Progress

A new research framework called TRACED evaluates LLM reasoning quality by analyzing geometric progress and stability of reasoning traces. It distinguishes correct reasoning from hallucinations based on trajectory patterns, offering a more robust evaluation method than scalar probabilities.

Jun 16, 2026 1 source
Fast-dLLM++ Boosts Diffusion LLM Inference Up to 37% With Fréchet Profile Decoding Technology
Artificial Intelligence #diffusion llm#inference

Fast-dLLM++ Boosts Diffusion LLM Inference Up to 37% With Fréchet Profile Decoding

Researchers propose Fast-dLLM++, a training-free extension to Fast-dLLM that uses Fréchet profile decoding to select parallel token commit sets from the full confidence profile. Experiments on LLaDA-8B show up to 37% higher throughput at comparable accuracy on benchmarks including GSM8K, MATH, HumanEval, and MBPP.

Jun 16, 2026 1 source
SDS-LoRA: New Low-Rank Adaptation Method Fixes Gradient Distortion in Large Model Fine-Tuning Technology
Artificial Intelligence #machine learning#low-rank adaptation

SDS-LoRA: New Low-Rank Adaptation Method Fixes Gradient Distortion in Large Model Fine-Tuning

A new paper on arXiv introduces SDS-LoRA, a low-rank parameterization that overcomes anisotropic gradient scaling in LoRA. By structurally decoupling singular values from the backward pass, SDS-LoRA ensures gradients are only applied through orthonormal bases, improving convergence and reducing the performance gap to full fine-tuning. Experimental results across natural language and vision benchmarks show enhanced adaptation performance.

Jun 16, 2026 1 source
Self-Gated Clarification Method Boosts AI Accuracy in Complex Tariff Classification Technology
Artificial Intelligence #artificial intelligence#language models

Self-Gated Clarification Method Boosts AI Accuracy in Complex Tariff Classification

Researchers propose ACTION-RATING, a self-gated clarification formulation that enables hierarchical language agents to decide when to ask for help during decision-making. Tested on Harmonized Tariff Schedule classification across nine LLMs, the method improved Information-Seeking Effectiveness from 50% to 74% and achieved up to +16.2% accuracy gains at the 10-digit level.

Jun 16, 2026 1 source
G-Loss: New Graph-Guided Loss Function Boosts Language Model Fine-Tuning Accuracy Technology
Artificial Intelligence #graph-guided#fine-tuning

G-Loss: New Graph-Guided Loss Function Boosts Language Model Fine-Tuning Accuracy

Researchers introduce G-Loss, a graph-guided loss function that leverages global semantic relationships to fine-tune language models more effectively than traditional loss functions, showing improved accuracy and faster convergence on five benchmark datasets.

Jun 16, 2026 1 source
Self-Consistency Reranking Boosts Accuracy in Narrative Question Answering for Enterprise AI Technology
Artificial Intelligence #self-consistency#reranking

Self-Consistency Reranking Boosts Accuracy in Narrative Question Answering for Enterprise AI

Researchers propose a self-consistency-based reranking framework for narrative question answering that generates multiple candidates and selects the final answer by semantic agreement. On the NarrativeQA dataset, FLAN-T5-Base improved from 82.32% to 86.66%, and Pegasus-Large jumped from 72.50% to 87.07%. The method requires no architectural changes, making it a drop-in enhancement for enterprise language models.

Jun 16, 2026 1 source
ArtNet: JEPA-Like Articulatory Framework Achieves 20.56% Error Reduction in Zero-Shot Phoneme Recognition Technology
Artificial Intelligence #artificial intelligence#phoneme recognition

ArtNet: JEPA-Like Articulatory Framework Achieves 20.56% Error Reduction in Zero-Shot Phoneme Recognition

Researchers propose ArtNet, a JEPA-like framework for zero-shot cross-lingual phoneme recognition. By integrating an articulatory predictor with a variational information bottleneck, ArtNet suppresses language-specific variations. Experiments on seven unseen languages show a 20.56% relative reduction in phoneme error rate and 7.01% in phoneme feature error rate.

Jun 16, 2026 1 source
P3B3 Benchmark Reveals Strong Brazilian Portuguese Bias in Large Language Models Technology
Artificial Intelligence #llm#benchmark

P3B3 Benchmark Reveals Strong Brazilian Portuguese Bias in Large Language Models

According to a new research paper, a team introduced P3B3, an expert-curated benchmark for measuring bias between European and Brazilian Portuguese in large language models. Experiments show most LLMs strongly prefer Brazilian Portuguese, underscoring the need for more balanced variety representation in conversational AI.

Jun 16, 2026 1 source
New Research Reveals Truthfulness Preserved Across LLM Lineages, Enabling Better Hallucination Control Technology
Artificial Intelligence #ai#artificial intelligence

New Research Reveals Truthfulness Preserved Across LLM Lineages, Enabling Better Hallucination Control

A new paper from researchers shows that truthfulness-related attention heads are preserved across generations of large language models, even after instruction tuning or multimodal adaptation. The authors propose TruthProbe, a soft-gating strategy that amplifies these heads to reduce hallucinations, with improvements on HaluEval, POPE, and CHAIR benchmarks.

Jun 16, 2026 1 source
DeepRoot Multi-Agent System Enables Therapeutic Reasoning Over Historical Medical Texts with 47.6% Accuracy Technology
Artificial Intelligence #deeproot#multi-agent system

DeepRoot Multi-Agent System Enables Therapeutic Reasoning Over Historical Medical Texts with 47.6% Accuracy

DeepRoot is a multi-agent LLM system that jointly builds and utilizes a verified knowledge graph for therapeutic reasoning over historical medical texts. Applied to the Shen Nong Ben Cao Jing, it recovers 10 of 21 held-out compound-disease treatment pairs at R@20 (47.6%), significantly outperforming a raw corpus LLM (4.8%) and random baseline (2.4%). The system also reduces hallucination to 7-10% compared to 87% for tool-using LLMs, offering a scalable method for mining historical medical knowledge.

Jun 16, 2026 1 source
LLM-Encoded Knowledge Guides Federated Graph Recommendation to Improve Accuracy Technology
Artificial Intelligence #federated learning#graph recommendation

LLM-Encoded Knowledge Guides Federated Graph Recommendation to Improve Accuracy

Researchers propose a federated graph recommendation framework that leverages LLM-encoded semantic knowledge to guide cross-client structural aggregation, addressing the challenge of non-IID client data. The method consistently outperforms existing federated graph baselines on standard benchmarks.

Jun 16, 2026 1 source
AdaMame: New Training Recipe Solves Language Collapse in Multilingual Reasoning Models Technology
Artificial Intelligence #artificial intelligence#multilingual

AdaMame: New Training Recipe Solves Language Collapse in Multilingual Reasoning Models

AdaMame, a two-stage training recipe for multilingual mathematical reasoning, addresses language collapse in large reasoning models. It adaptively aligns reasoning language to the query language without compromising accuracy, achieving Pareto-optimal performance across 12 languages.

Jun 16, 2026 1 source
MMLongEmbed Benchmark Reveals Limitations in Long-Context Multimodal Embedding Models Technology
Artificial Intelligence #multimodal#embedding

MMLongEmbed Benchmark Reveals Limitations in Long-Context Multimodal Embedding Models

MMLongEmbed is the first comprehensive benchmark for evaluating multimodal embedding models (MEMs) in long-context scenarios. It comprises four retrieval tasks covering text, document, and video modalities. The evaluation reveals that current MEMs rely heavily on superficial feature matching and struggle with deep semantic and structural dependencies, with performance degrading systematically based on context length and key information placement.

Jun 16, 2026 1 source
New Self-Enhanced Fine-Tuning Method Boosts Text-to-SQL Reasoning and Generalization Technology
Artificial Intelligence #text-to-sql#reasoning

New Self-Enhanced Fine-Tuning Method Boosts Text-to-SQL Reasoning and Generalization

Researchers propose CoTE-SQL, a self-enhanced fine-tuning method that improves text-to-SQL generation by integrating reasoning traces, structured chain-of-thought prompting, and execution error correction. The approach achieves state-of-the-art results on Bird and Spider benchmarks, particularly on complex queries.

Jun 16, 2026 1 source
New Method Resolves Drift Attribution Ambiguity in LLM Evaluation Pipelines Technology
Artificial Intelligence #llm evaluation#drift detection

New Method Resolves Drift Attribution Ambiguity in LLM Evaluation Pipelines

A research paper introduces an anytime-valid attribution method for LLM evaluation pipelines that resolves the ambiguity between product drift and judge model changes. Using a fixed human-labeled anchor set and betting e-processes, the method achieved zero misattribution on silent version bumps and correctly attributed prompt changes in 110 of 120 runs, while the industry-default rolling z-test false-alarmed on 75% of drift-free streams.

Jun 16, 2026 1 source
EHRNote-ChatQA: New Benchmark Tests LLMs on Multi-Turn Clinical Question Answering Technology
Artificial Intelligence #ehr#clinical

EHRNote-ChatQA: New Benchmark Tests LLMs on Multi-Turn Clinical Question Answering

Researchers introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over multiple discharge summaries. Built from MIMIC-IV data, it contains 967 patient-level samples and 16,072 QA pairs, revealing that LLMs struggle more with evidence grounding than content answering and that multi-turn errors compound.

Jun 16, 2026 1 source
Koshur Diacritizer: A Byte-Level Model Restores Diacritics for Kashmiri Language NLP Technology
Artificial Intelligence #kashmiri#diacritic restoration

Koshur Diacritizer: A Byte-Level Model Restores Diacritics for Kashmiri Language NLP

Researchers have developed Koshur Diacritizer, a byte-level sequence-to-sequence model based on ByT5-small, to restore missing diacritic marks in Kashmiri digital text. The model, trained on 23,700 sentence pairs, achieves a DERm of 0.2012 and word error rate of 0.2159, with a native expert accuracy of 77.5%. The dataset, model, and source code are publicly released to support low-resource language research.

Jun 16, 2026 1 source
Researchers Tackle Annotator Disagreement to Improve Hate Speech Classification Accuracy Technology
Artificial Intelligence #hate speech#annotator disagreement

Researchers Tackle Annotator Disagreement to Improve Hate Speech Classification Accuracy

A new research paper from Dehghan, Sen, and Yanikoglu explores the challenge of annotator disagreement in hate speech classification. The authors evaluate aggregation methods like majority voting and ordinal strategies, demonstrating that filtering non-consensus samples leads to over-optimistic results and that leveraging perceived hate speech strength enhances performance. They establish new state-of-the-art results for Turkish tweets.

Jun 16, 2026 1 source
Data Augmentations Offer Path to Efficient Language Model Pretraining Under Data Constraints Technology
Artificial Intelligence #data augmentation#language model

Data Augmentations Offer Path to Efficient Language Model Pretraining Under Data Constraints

As AI labs face a data ceiling where compute capacity outpaces new high-quality text, researchers propose data augmentations to enable productive multi-epoch training on fixed corpora. Three categories—token-level noise, sequence permutations, and target offset prediction—are shown to delay overfitting and lower validation loss compared to standard autoregressive pretraining. Random token replacement achieved the best minimum loss among individual methods, with combined augmentations further improving results.

Jun 16, 2026 1 source
Few-Shot Biomedical Relation Extraction with LLMs: A Viable Alternative to Supervised Learning? Technology
Artificial Intelligence #few-shot learning#biomedical relation extraction

Few-Shot Biomedical Relation Extraction with LLMs: A Viable Alternative to Supervised Learning?

A new study on arXiv investigates few-shot biomedical relation extraction using large language models (LLMs). The best model achieved micro-F1 of 0.44, surpassing prior few-shot results but below supervised baseline. However, on macro-F1, prompt-based methods outperformed supervised learning, particularly on rare relation types, highlighting LLMs' potential in low-resource settings.

Jun 16, 2026 1 source