Artificial Aphasias in Lesioned Language Models
Researchers apply an aphasia-inspired 'lesioning' technique to five 1B-scale language models by zeroing out model parameters and measuring resulting language impairments against a Text Aphasia Battery (TAB). Across 112,426 outputs, the full range of aphasia symptoms emerges but in distributions distinct from human aphasia profiles. The study finds systematic differences between attention components (query, key, value, output) and feed-forward components, as well as depth-dependent effects where early-layer lesions cause syntactic/semantic symptoms and late-middle layers yield phonological and fluency deficits. The qualitative divergence between LM and human aphasia patterns suggests aphasia syndromes are shaped by learning and processing details rather than being universal consequences of disrupted language processing.
Related guides (1)
Related events (8)
Why Language Models Hallucinate
OpenAI published research explaining the mechanisms behind language model hallucination. The work connects improved evaluation methods to enhanced AI reliability, honesty, and safety. The body is sparse on technical detail, but the framing positions this as foundational research relevant to alignment and deployment trust.
Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions
This paper investigates whether language models can learn the semantics of rare English constructions (e.g., 'let alone', 'much less'), constructing a novel dataset to test form-meaning pairing understanding. Testing models across parameter counts, architectures, and pretraining dataset sizes, the authors find that modestly sized open-source models can grasp Paired-Focus construction semantics, while models trained on human-scale data fail. Training dynamics analysis reveals that semantic understanding of these constructions emerges later than syntactic knowledge and correlates with gains in world knowledge more broadly.
Trajectory Analysis of Masked Diffusion LMs for Graph-to-Text Generation with Lambda-Scaled Structural Decoding
This paper presents the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation, analyzing the order in which tokens are unmasked during iterative decoding. The authors find MDLMs naturally unmask entities first, then relational/function words, then structural tokens—a pattern disrupted by supervised fine-tuning, which prematurely anchors structural tokens and causes hallucination or omission. They propose lambda-scaled structural decoding, a training-free inference-time fix that recovers +9.4 BLEU-4, and introduce Graph-LLaDA, which integrates a Graph Transformer encoder into LLaDA's decoding process. Cross-dataset evaluation on the LAGRANGE benchmark shows prior baselines overfit to dataset-specific patterns while MDLM-based approaches generalize better.
Scaling Laws for Neural Language Models
OpenAI published foundational research establishing empirical scaling laws for neural language models, showing that model performance scales predictably with compute, data, and parameters. The work demonstrated power-law relationships between these factors and loss, providing a principled framework for allocating training resources. This paper became a cornerstone of modern large language model development strategy.
Systematic study reveals effectiveness-fluency trade-offs in LLM conditioning methods
A new arXiv paper systematically evaluates a range of LLM conditioning methods across both concept injection and removal scenarios, finding that efficient steering methods often degrade fluency significantly. A key finding is that activation steering is substantially less effective on instruction-tuned models than on base models, a previously overlooked interaction. Simple prompting and supervised fine-tuning work for concept injection but not removal, and cheap textual metrics are found to correlate well with expensive LLM-as-judge evaluations.
Lessons learned on language model safety and misuse
OpenAI published a post summarizing their evolving thinking on language model safety and misuse in deployed systems. The piece is intended to share lessons with other AI developers facing similar challenges. It covers OpenAI's internal approaches to mitigating harmful outputs and misuse patterns observed in production.
Language-Switching Backdoor Triggers Use Orthogonal Latent Subspace in LLMs
Researchers identify and decompose the internal circuit underlying a language-switching backdoor attack in an 8B-parameter autoregressive language model, where a three-word Latin trigger redirects English output to French. The circuit operates in three phases: early attention heads compose trigger tokens, a mid-layer signal propagates through a subspace orthogonal to the model's natural language-identity direction, and a final MLP layer converts the latent signal into French logits. The entire circuit flows through a serial bottleneck at a single sequence position, meaning corrupting that position mitigates the trigger but also degrades general capabilities. Critically, the orthogonal encoding means defenses that search for language-like signals in intermediate representations would fail to detect this trigger.
Synthetic LLM-generated conversations improve ASR training for low-resource languages
Researchers propose a pipeline that uses LLMs to generate scenario-level dialogues and TTS to synthesize multi-speaker audio, creating simulated conversational training data for ASR systems. Evaluated on the Hungarian BEA-Dialogue benchmark, a model trained on 67 hours of real plus 636 hours of synthetic data outperforms a zero-shot model trained on 2,700 hours of real Hungarian speech. The study tests five LLM families under multiple budget and mixing configurations using a FastConformer-Large backbone, finding that generator choice and data composition significantly affect gains.