We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
This paper takes a position on how anti-misinformation AI works should be developed for the online misinformation context. We observe that t… (see more)he current literature is dominated by works that produce more information for users to process and that this function faces various challenges in bringing meaningful effects to reality. We use anti-misinformation insights from other domains to suggest a redirection of the existing line of work and identify an under-explored opportunity AI can facilitate exploring.
This paper takes a position on how anti-misinformation AI works should be developed for the online misinformation context. We observe that t… (see more)he current literature is dominated by works that produce more information for users to process and that this function faces various challenges in bringing meaningful effects to reality. We use anti-misinformation insights from other domains to suggest a redirection of the existing line of work and identify an under-explored opportunity AI can facilitate exploring.
Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from e… (see more)rosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses only on "correctness" and often overlooks "consistency", necessary to distinguish and address these harms. To bridge this gap, we introduce _prompt multiplicity_, a framework for quantifying consistency through prompt sensitivity. Our analysis reveals significant multiplicity (over 50% inconsistency in benchmarks like Med-HALT), suggesting that hallucination-related harms have been severely underestimated. Furthermore, we study the role of consistency in hallucination detection and mitigation. We find that: (a) detection techniques capture consistency, not correctness, and (b) mitigation techniques like RAG can introduce additional inconsistencies. By integrating prompt multiplicity into hallucination evaluation, we provide an improved framework of potential harms and uncover critical limitations in current detection and mitigation strategies.
Transition path sampling (TPS) is an important method for studying rare events, such as they happen in chemical reactions or protein folding… (see more). These events occur so infrequently that traditional simulations are often impractical, and even recent machine-learning approaches struggle to address this issue for larger systems. In this paper, we propose using modern deep learning techniques to improve the scalability of TPS methods significantly. We highlight the need for better evaluations in the existing literature and start by formulating TPS as a sampling problem over an unnormalized target density and introduce relevant evaluation metrics to assess the effectiveness of TPS solutions from this perspective. To develop a scalable approach, we explore several design choices, including a problem-informed neural network architecture, simulated annealing, the integration of prior knowledge into the sampling process, and attention mechanisms. Finally, we conduct a comprehensive empirical study and compare these design choices with other recently developed deep-learning methods for rare event sampling.
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values… (see more) - a process coined alignment. However, aligning LLMs remains challenging due to the inherent disconnect between the complexity of human values and the narrow nature of the technological approaches designed to address them. Current alignment methods often lead to misspecified objectives, reflecting the broader issue of incomplete contracts, the impracticality of specifying a contract between a model developer, and the model that accounts for every scenario in LLM alignment. In this paper, we argue that improving LLM alignment requires incorporating insights from societal alignment frameworks, including social, economic, and contractual alignment, and discuss potential solutions drawn from these domains. Given the role of uncertainty within societal alignment frameworks, we then investigate how it manifests in LLM alignment. We end our discussion by offering an alternative view on LLM alignment, framing the underspecified nature of its objectives as an opportunity rather than perfect their specification. Beyond technical improvements in LLM alignment, we discuss the need for participatory alignment interface designs.
Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Existing hallucination benchmarks often o… (see more)verlook prompt sensitivity, due to stable accuracy scores despite prompt variations. However, such stability can be misleading. In this work, we introduce prompt multiplicity--the multiplicity of individual hallucinations depending on the input prompt--and study its role in LLM hallucination benchmarks. We find severe multiplicity, with even more than 50% of responses changing between correct and incorrect answers simply based on the prompt for certain benchmarks, like Med-HALT. Prompt multiplicity also gives us the lens to distinguish between randomness in generation and consistent factual inaccuracies, providing a more nuanced understanding of LLM hallucinations and their real-world harms. By situating our discussion within existing hallucination taxonomies--supporting their quantification--and exploring its relationship with uncertainty in generation, we highlight how prompt multiplicity fills a critical gap in the literature on LLM hallucinations.
Dynamically integrating new or rapidly evolving information after Language Model (LM) pre-training remains challenging, particularly in low-… (see more)data scenarios or when dealing with private and specialized documents. In-context learning and retrieval-augmented generation (RAG) face limitations, including their high inference costs and their inability to capture global document information. In this paper, we propose a way of modularizing knowledge by training Knowledge Modules (KMs). KMs are lightweight components implemented as parameter-efficient LoRA modules, which are trained to store information about new documents and can be easily plugged into models on demand. We show that next-token prediction performs poorly in training KMs. We instead propose Deep Context Distillation: we learn KMs parameters such as to simulate hidden states and logits of a teacher that takes the document in context. Our method outperforms standard next-token prediction and pre-instruction training techniques, across two datasets. Finally, we highlight synergies between KMs and retrieval-augmented generation.
Type inference for dynamic languages like Python is a persistent challenge in software engineering. While large language models (LLMs) have … (see more)shown promise in code understanding, their type inference capabilities remain underexplored. We introduce `TypyBench`, a benchmark designed to evaluate LLMs' type inference across entire Python repositories. `TypyBench` features two novel metrics: `TypeSim`, which captures nuanced semantic relationships between predicted and ground truth types, and `TypeCheck`, which assesses type consistency across codebases. Our evaluation of various LLMs on a curated dataset of 50 high-quality Python repositories reveals that, although LLMs achieve decent `TypeSim` scores, they struggle with complex nested types and exhibit significant type consistency errors. These findings suggest that future research should shift focus from improving type similarity to addressing repository-level consistency. `TypyBench` provides a foundation for this new direction, offering insights into model performance across different type complexities and usage contexts.
Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. … (see more)Although steering demonstrates promising performance, recent work shows that it can be unreliable or even counterproductive in some cases. This paper studies the influence of prompt types and the geometry of activation differences on steering reliability. First, we find that all seven prompt types used in our experiments produce a net positive steering effect, but exhibit high variance across samples, and often give an effect opposite of the desired one. No prompt type clearly outperforms the others, and yet the steering vectors resulting from the different prompt types often differ directionally (as measured by cosine similarity). Second, we show that higher cosine similarity between training set activation differences predicts more effective steering. Finally, we observe that datasets where positive and negative activations are better separated are more steerable. Our results suggest that vector steering is unreliable when the target behavior is not represented by a coherent direction.
As multilingual generative models become more widely used, most safety and fairness evaluation techniques still focus on English-language re… (see more)sources, while overlooking important cross-cultural factors. This limitation raises concerns about fairness and safety, particularly regarding geoculturally situated stereotypes that hinder the models’ global inclusivity. In this work, we present preliminary findings on the impact of stereotype unlearning across languages, specifically in English, French, and Hindi. Using an adapted version of the SeeGULL dataset, we analyze how unlearning stereotypes in one language influences other languages within multilingual large language models. Our study evaluates two model families, Llama-3.1-8B and Aya-Expanse-8B, to assess whether unlearning in one linguistic context transfers across languages, potentially mitigating or exacerbating biases in multilingual settings.
Understanding diverse web data and automating web development presents an exciting challenge for agentic AI. While existing benchmarks addre… (see more)ss isolated web-based tasks—such as website-based Visual Question Answering (VQA) and UI-to-code generation—they lack a unified evaluation suite for assessing web agents that interact with and reason about web environments. We introduce WebMMU, a large-scale benchmark for evaluating AI-driven web agents across multilingual website VQA, HTML/CSS/JavaScript code editing, and sketch-to-code generation. WebMMU provides a comprehensive evaluation suite with real-world website data, multi-step reasoning tasks, and functional UI understanding. Benchmarking state-of-the-art multimodal models on WebMMU reveals significant limitations in web-based reasoning, layout understanding, and structured code generation, particularly in preserving UI hierarchy, handling multilingual content, and producing robust, functional code. While most existing models are optimized for English-only settings, WebMMU highlights the challenges of cross-lingual adaptation in real-world web development. These findings expose critical gaps in current models’ ability to understand website structures, execute user instructions, and generate high-quality web code, underscoring the need for more advanced multimodal reasoning in AI-driven web understanding and development.
