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.)?
Publications
A Generative Approach to LLM Harmfulness Detection with Red Flag Tokens
Most safety training methods for large-language models (LLMs) based on fine-tuning rely on dramatically changing the output distribution of … (see more)the model when faced with a harmful request, shifting it from an unsafe answer to a refusal to respond.
These methods inherently compromise model capabilities and might make auto-regressive models vulnerable to attacks that make likely an initial token of affirmative response.
To avoid that, we propose to expand the model's vocabulary with a special token we call a *red flag token* (
Grokking refers to a delayed generalization following overfitting when optimizing artificial neural networks with gradient-based methods.
I… (see more)n this work, we demonstrate that grokking can be induced by regularization, either explicit or implicit. More precisely, we show that when there exists a model with a property
Grokking refers to a delayed generalization following overfitting when optimizing artificial neural networks with gradient-based methods.
I… (see more)n this work, we demonstrate that grokking can be induced by regularization, either explicit or implicit. More precisely, we show that when there exists a model with a property
Misinformation is a complex societal issue, and mitigating solutions are difficult to create due to data deficiencies. To address this probl… (see more)em, we have curated the largest collection of (mis)information datasets in the literature, totaling 75. From these, we evaluated the quality of all of the 36 datasets that consist of statements or claims, as well as the 9 datasets that consists of data in purely paragraph form. We assess these datasets to identify those with solid foundations for empirical work and those with flaws that could result in misleading and non-generalizable results, such as insufficient label quality, spurious correlations. We further provide state-of-the-art baselines on all these datasets, but show that regardless of label quality, categorical labels may no longer give an accurate evaluation of detection model performance. We discuss alternatives to mitigate this problem. Overall, this guide aims to provide a roadmap for obtaining higher quality data and conducting more effective evaluations, ultimately improving research in misinformation detection. All datasets and other artifacts are available at [anonymized].
Numerous applications of large language models (LLMs) rely on their ability to perform step-by-step reasoning. However, the reasoning behavi… (see more)or of LLMs remains poorly understood, posing challenges to research, development, and safety. To address this gap, we introduce landscape of thoughts-the first visualization tool for users to inspect the reasoning paths of chain-of-thought and its derivatives on any multi-choice dataset. Specifically, we represent the states in a reasoning path as feature vectors that quantify their distances to all answer choices. These features are then visualized in two-dimensional plots using t-SNE. Qualitative analysis shows that the landscape of thoughts effectively distinguishes between strong and weak models, correct and incorrect answers, as well as different reasoning tasks. It also uncovers undesirable reasoning patterns, such as low consistency and high uncertainty. Additionally, users can adapt our tool to a neural model that predicts any property they observe. We showcase this advantage by adapting our tool to a lightweight verifier, which significantly improves reasoning by evaluating the correctness of reasoning paths.
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not… (see more) guaranteed to be correct. Expert recommendations may contradict data-driven results, and their reliability can vary significantly depending on the domain or specific query. Existing methods based on soft constraints or inconsistencies in predicted causal relationships fail to account for these variations in expertise. To remedy this, we propose L2D-CD, a method for gauging the correctness of expert recommendations and optimally combining them with data-driven causal discovery results. By adapting learning-to-defer (L2D) algorithms for pairwise causal discovery (CD), we learn a deferral function that selects whether to rely on classical causal discovery methods using numerical data or expert recommendations based on textual meta-data. We evaluate L2D-CD on the canonical Tübingen pairs dataset and demonstrate its superior performance compared to both the causal discovery method and the expert used in isolation. Moreover, our approach identifies domains where the expert's performance is strong or weak. Finally, we outline a strategy for generalizing this approach to causal discovery on graphs with more than two variables, paving the way for further research in this area.
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not… (see more) guaranteed to be correct. Expert recommendations may contradict data-driven results, and their reliability can vary significantly depending on the domain or specific query. Existing methods based on soft constraints or inconsistencies in predicted causal relationships fail to account for these variations in expertise. To remedy this, we propose L2D-CD, a method for gauging the correctness of expert recommendations and optimally combining them with data-driven causal discovery results. By adapting learning-to-defer (L2D) algorithms for pairwise causal discovery (CD), we learn a deferral function that selects whether to rely on classical causal discovery methods using numerical data or expert recommendations based on textual meta-data. We evaluate L2D-CD on the canonical Tübingen pairs dataset and demonstrate its superior performance compared to both the causal discovery method and the expert used in isolation. Moreover, our approach identifies domains where the expert's performance is strong or weak. Finally, we outline a strategy for generalizing this approach to causal discovery on graphs with more than two variables, paving the way for further research in this area.
Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on… (see more) single-objective reinforcement learning, limiting their applicability to real-world drug design, where multiple competing properties must be optimized. Traditional multi-objective reinforcement learning (MORL) methods require costly retraining for each new objective combination, making rapid exploration of trade-offs impractical. To overcome these limitations, we introduce Mol-MoE, a mixture-of-experts (MoE) architecture that enables efficient test-time steering of molecule generation without retraining. Central to our approach is a preference-based router training objective that incentivizes the router to combine experts in a way that aligns with user-specified trade-offs. This provides improved flexibility in exploring the chemical property space at test time, facilitating rapid trade-off exploration. Benchmarking against state-of-the-art methods, we show that Mol-MoE achieves superior sample quality and steerability.
Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of
AI systems by constraining their decisions on a set of human-unde… (see more)rstandable
concepts. However, CBMs typically assume that datasets contain accurate concept
labels—an assumption often violated in practice, which we show can significantly
degrade performance (by 25% in some cases). To address this, we introduce the
Concept Preference Optimization (CPO) objective, a new loss function based on
Direct Preference Optimization, which effectively mitigates the negative impact
of concept mislabeling on CBM performance. We provide an analysis of some
key properties of the CPO objective showing it directly optimizes for the concept’s
posterior distribution, and contrast it against Binary Cross Entropy (BCE) where
we show CPO is inherently less sensitive to concept noise. We empirically confirm
our analysis finding that CPO consistently outperforms BCE in three real-world
datasets with and without added label noise.
Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of
AI systems by constraining their decisions on a set of human-unde… (see more)rstandable
concepts. However, CBMs typically assume that datasets contain accurate concept
labels—an assumption often violated in practice, which we show can significantly
degrade performance (by 25% in some cases). To address this, we introduce the
Concept Preference Optimization (CPO) objective, a new loss function based on
Direct Preference Optimization, which effectively mitigates the negative impact
of concept mislabeling on CBM performance. We provide an analysis of some
key properties of the CPO objective showing it directly optimizes for the concept’s
posterior distribution, and contrast it against Binary Cross Entropy (BCE) where
we show CPO is inherently less sensitive to concept noise. We empirically confirm
our analysis finding that CPO consistently outperforms BCE in three real-world
datasets with and without added label noise.
