Inspired by recent breakthroughs in Large Language Models (LLMs), this work introduces LLP, the first LLM-based generative framework for second-hand product pricing that substantially surpasses existing methods while generalizing well to unseen categories.
A variant of FocusAgent significantly reduces the success rate of prompt-injection attacks, including banner and pop-up attacks, while maintaining task success performance in attack-free settings, highlighting that targeted LLM-based retrieval is a practical and robust strategy for building web agents that are efficient, effective, and secure.
Imene Kerboua, S. Shayegan, Megh Thakkar et al.· arXiv.org· 15 citations
This work conducts the first large-scale, systematic studies of multilingual calibration across six model families and over 100 languages, revealing that non-English languages suffer from systematically worse calibration.
Ej Zhou, Caiqi Zhang, Tiancheng Hu et al.· arXiv.org· 10 citations· ⚡1
This work finds that self bias arises from two compounding sources, LLM as a testset and LLM as an evaluator, and their combination amplifies the effect and confirms that the phenomenon extends to open-ended generation on the Chatbot Arena task.
Wenda Xu, Sweta Agrawal, Vilém Zouhar et al.· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Transformer Encoder Tree is introduced, a hierarchical, non-autoregressive encoder-only architecture trained with Connectionist Temporal Classification for multilingual translation that eliminates the sequential bottleneck of autoregressive models and supports fully parallel decoding of all tokens across all target languages.
Yiwen Guan, Jacob Whitehill· arXiv.org· 0 citations
Compared to existing DP text generation baselines, Term2Note substantially improves both fidelity and utility, without relying on label distribution assumptions, highlighting its effectiveness as a practical privacy-preserving alternative to real clinical notes.
Yuping Wu, Viktor Schlegel, Warren Del-Pinto et al.· 2 citations
The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains scarce. Here we introduce MAGneT, a novel multi-agent framework for synthetic psychological counseling session generation that decomposes counselor response generation into coordinated sub-tasks handled by specialized LLM agents, each modeling a key psychological technique. Unlike prior single-agent approaches, MAGneT better captures the structure and nuance of real counseling. We further propose a unified evaluation framework that consolidates diverse automatic metrics and expands expert assessment from four to nine counseling aspects, thus addressing inconsistencies in prior evaluation protocols. Empirically, MAGneT substantially outperforms existing methods: experts prefer MAGneT-generated sessions in 77.2% of cases on average across the nine aspects over the strongest baseline, and sessions generated by MAGneT using Llama3-8B-Instruct backbone yield 3.2% higher general counseling skills and 4.3% higher CBT-specific skills on cognitive therapy rating scale (CTRS). An open source Llama3-8B-Instruct model fine-tuned on MAGneT-generated data also outperforms models fine-tuned using baseline synthetic datasets by 6.9% on average on CTRS. We make our code, data and fine-tuned model public.
Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological biases. In this work, we examine how synthetic persona conditioning shapes ideological expression across seven open-weight instruction-tuned models (7B-72B parameters) using the Political Compass Test (62 statements) as a standardized behavioral probe. Across three studies involving 200,000 synthetic personas and more than 260 million model responses, we analyze implicit and explicit malleability, as well as theme-associated variations. We find that: (i) larger models exhibit broader implicit ideological coverage, increasing from 14-35% for 7-8B models to up to 49% for 70B+ models; (ii) explicit ideological priming induces large and statistically significant shifts, with right-authoritarian cues moving all models in the intended direction and producing larger effects in most model-axis comparisons; (iii) left-libertarian priming produces more heterogeneous responses, including counter-directional economic shifts in three of four 7-8B models, while all 70B+ models move in the intended direction; and (iv) theme-associated semantic content in persona descriptions is linked to systematic and interpretable directional shifts in ideological space. While our results identify an upstream mechanism through which persona conditioning can alter model responses under a standardized ideological probe, we do not test whether such shifts affect users beliefs, decisions, or political behavior. Our findings are best understood as evidence of ideological malleability at the generation layer, highlighting the need to account for interactional factors when evaluating political neutrality, fairness, and safety in English-prompted, persona-conditioned language models.
Pietro Bernardelle, Stefano Civelli, Leon Fröhling et al.· Information Processing &...· 5 citations
Behavior Aligned Retrieval (BAR) is proposed, a backbone-agnostic training recipe that teaches a dense retriever a behavior-aware similarity, keeping semantically related candidates close only when their tool-use behavior is compatible.
This work introduces Scientific Introduction Generation (SciIG), a task that evaluates LLMs'ability to produce coherent introductions from titles, abstracts, and related works, and combines automated metrics with LLM-as-a-judge evaluations.
Krishna Garg, Firoz Shaik, Sambaran Bandyopadhyay et al.· 5 citations
The introduction of MM-BrowseComp, a novel benchmark comprising 400 challenging, hand-crafted questions designed to evaluate multimodal retrieval and reasoning capabilities, is introduced, establishing MM-BrowseComp as a rigorous new standard for the field.
Shilong Li, Xingyuan Bu, Wenjie Wang et al.· arXiv.org· 37 citations· ⚡7
This research extends an existing multilingual LLM (Llama-3-8B) to get a better coverage for Sinhala and enhances the LLM tokenizer with Sinhala specific vocabulary and performs continual pre-training on a 10 million sentence Sinhala corpus, resulting in the SinLlama model.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
