Natural Language Processing

Researchers have developed MedExpMem, an experience memory framework that enables medical vision-language models to accumulate differential diagnosis expertise from their own diagnostic failures. The system, which mirror…

Researchers developed a graph neural network that models alignment topology between reference documents and LLM outputs to detect hallucinations, achieving state-of-the-art results on four datasets. The method outperform…

A new study evaluating large language models in the social deduction game Secret Hitler found that current architectures remain ineffective at complex, multi-turn manipulation and deception. Models like Llama 3.1 70B ach…

Researchers tested seven large language models on their ability to infer employee expertise from 27,188 Slack messages, finding that Gemini 2.5 Flash achieved the lowest estimation error at 21.13% mean absolute error. Th…

A new study published on arXiv demonstrates that model collapse in large language models (LLMs) — the progressive degradation of models trained on their own outputs — follows predictable patterns of cultural evolution. R…

A study of fMRI data from 112 English, Chinese, and French speakers found that brain-LLM alignment is driven by training-language dominance, not an inherent property of English. A Chinese-dominant model reversed the alig…

Researchers introduced Reflection-Augmented Scaling (RAS), a method that uses execution error messages from databases to improve Cypher query generation through in-context learning. Testing across three Neo4j datasets an…

A new computational study provides causal evidence that large language models acquire knowledge of unacceptable grammatical constructions through statistical preemption, a mechanism previously theorized in Construction G…

Researchers introduced parallel context compaction for long-horizon LLM agent serving, addressing the problem of growing conversation histories exceeding context windows. The method provides fine-grained, predictable con…

Researchers have developed a principled method for multilingual language steering in large language models using sparse autoencoders (SAEs), addressing the unreliability of existing English-only SAE approaches. By traini…

Researchers have introduced Transcoders, a function-centric framework that decomposes vision-language models into interpretable computational pathways linking image patches to token generation. Applied to Gemma 3-4B-IT, …

Researchers have identified a fundamental flaw in how AI agents are evaluated for knowledge work, finding that higher benchmark scores do not reliably indicate real-world performance. The team proposes a three-step frame…

Researchers have developed TPA (Think, Plan, Ask), a proactive multi-agent dialogue framework that enables large language models to systematically select questioning strategies to surface latent social language disorder …

A new study found that large language models (LLMs) exhibit systematic and reproducible biases when advising on religious conversions, consistently favoring some faiths while discouraging others. Researchers tested 20 mo…

Researchers introduced PathCal, a training-free decoding controller that calibrates reasoning paths in large language models by distinguishing distinct types of reflection markers such as "wait" and "but." The system int…

A new study of small language models reveals that chain-of-thought prompting for arithmetic relies on a positional shortcut: the model copies whichever number appears last before the answer delimiter, regardless of the l…

Researchers have developed LIFT, a new fine-tuning algorithm for diffusion language models that improves reasoning capabilities by aligning token learning difficulty with the information available at different diffusion …

Researchers have developed a knowledge-aware Text-to-SQL framework that improves the performance of large language models in converting natural language questions into executable database queries, particularly in low-res…

Researchers at HASH built a 25M-parameter transformer decoder, vec2slug, that generates URL slugs directly from vector embeddings, achieving 14-19x faster and 85x cheaper performance than a Haiku-class LLM. The model ext…

The widespread use of large language models to generate written content is violating an implicit social contract between readers and writers, according to a new analysis from Oxide Computer. The company's Request for Dis…