Abliteration, the removal of refusal capabilities from large language models by projecting weight matrices orthogonal to an extracted refusal direction, has emerged as a prominent safety concern through its ability to bypass post-training alignment using only a small set of contrastive prompts. We find that existing defenses commonly overlook the cause of abliteration; that is, how easily the refusal direction can be extracted. To hinder this process, we introduce a weight-editing method that obscures the refusal signal by applying rank-$k$ updates to residual stream writer matrices while replacing refusal-inducing activations with random aliases and correcting downstream reader matrices to preserve the model's original behavior. On Llama-3-8B, AMRA improves post-abliteration refusal scores by $2.16$ points over the undefended baseline with less than $0.5$ percentage points of MMLU degradation. On Gemma-2-9B, it improves the post-abliteration refusal by $14.70$ points over the baseline while keeping harmful output rates similar to the baseline, albeit at a greater utility cost.
This work makes two contributions: 1) authorship attribution is a distinct driver of evaluation bias, and 2) open-ended, ground-truth-free tasks can serve as controlled instruments for studying LLM judge behavior.
Songeun Chae, Min Kim, Donghoon Jung et al.· 0 citations
This work shows how to find this valence axis (V-axis) from just 9 emotion category names plus 50 short narrative paragraphs per emotion -- about 1,500 fewer labels than the usual supervised approach -- and that the same direction appears in vision, audio, and human-brain encoders never jointly trained.
This work introduces Latent Space Refusal Anchoring (LSR-Anchoring), a training-free method that extracts the refusal direction from English prompts and clamps it onto the residual stream at inference time.
Godwin Abuh Faruna· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes SuTRA (Structurally-Unified Tokenization with Root Awareness), a morphology-aware algorithm that preserves akshara indivisibility and penalizes merges crossing morphological boundaries and releases a new morphological segmentation dataset for Hindi, Marathi, and Gujarati.
Vaibhav Rathore, Siddhant Gole, Dadhichi Telwadkar et al.· 0 citations
Analyzing a large corpus of publicly released post-training trajectories, it is found that across different tasks, the agent's training strategy is locked in at the very beginning, and the entire remaining budget is spent on local adjustments within the selected strategy.
J. Lim, Xinyuan Huang, Hao Peng et al.· 0 citations
An adaptive memory and reflection (AMR) agentic system, a multi-agent framework in which specialized agents use dedicated memory and reflection-based feedback to retrieve relevant prior cases and improve subsequent reasoning.
P. Murugesan, Luoxiao Yang, Xueli Chen et al.· 0 citations
EvalCEGAR is a pool of small Python operators that each flag a candidate for one named defect, or abstain, and vote, and borrows counterexample-guided abstraction refinement from program verification to score agents against a reliable automatic metric.
Xing Zhang, Ya Cui, Guanghui Wang et al.· 0 citations
BudgetDoc is introduced, the first multimodal benchmark providing explicit supervision for model-budget-performance trade-offs across three document tasks, and DRB (Document-Reasoning Balancer), an approx.
This work presents ComponentBench, a benchmark and diagnostic pipeline for component-level evaluation of computer-use agents on modern web UIs, and introduces a scalable pipeline for auditing realized structural difficulty after implementation and synthesizing structured failure analyses across tasks and component families.
Tianchen Guan, Xinlei Lin, Royce Cheng-Yue et al.· 0 citations
Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenges have become more urgent with novel EU legislation. Uncertainty around LLM usage with respect to privacy concerns in EU countries can be a major blocker for the speed of innovation and transfer from research to applications. Here we present \textbf{Redakto}, a tool that can be used for anonymizing text prior to feeding it to an LLM or other downstream text processing. We provide state-of-the-art functionalities for both redaction of PII but also when used for pseudonymization. These functionalities are exposed such that they can easily be used by end-users, through the Redakto web application, and by developers and researchers, via REST APIs and model context protocol (MCP) hooks. The implementation is fully open source, requires modest compute resources, and can be readily deployed on local hardware. In contrast to prior work and in order to better assess the quality of the anonymized texts, we conduct extensive empirical evaluations on textual data from legal and medical domain with respect to both privacy and utility of the redacted texts. Our empirical results demonstrate that the texts anonymized with different redaction strategies achieve utility scores on par with the original texts, suggesting that anonymization with Redakto can be used for LLM tasks without substantial negative impact for the tasks we explored.
Saurav Kumar Saha, Tom Röhr, F. Biessmann· 0 citations
It is challenging to detect hate speech in Low Resource Languages (LRLs) because of the absence of annotated data, the informality of its language structure, and the lack of standardized grammar. A good example of such a challenge is Roman Urdu which is broadly used by South Asians on social media and has a high variation while lacking contextually consistent spellings. The objective of this paper is to conduct a comprehensive assessment of Large Language Models (LLMs) for Hate Speech Detection (HSD) in Roman Urdu script and fine-tune these models using the Parameter-Efficient Fine-Tuning (PEFT) method called Low-Rank Adaptation (LoRA). To evaluate zero-shot inference, we benchmarked it against PEFT on different transformer models, including Mistral, LLaMA, Falcon, and multilingual BERT. Experiments are conducted on the PURUTT (Parallel Urdu and Roman Urdu Corpus for Toxic Comments and Transliteration) dataset with over 72,000 annotated comments. The results suggest that zero shot models perform moderately (F1 = 0.56), but updating a small fraction of the model trainable parameters improves the classification performance significantly (F1>0.93). Our results have shown that PEFT delivers outstanding performance alongside excellent computational efficiency, making it highly suitable for low-resource language processing tasks.
Toneema Zubair, Muhammad Asif, F. Kamiran et al.· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
