Related papers: Deceptive Automated Interpretability: Language Mod…

Deep-learning based Automatic Essay Scoring (AES) systems are being actively used by states and language testing agencies alike to evaluate millions of candidates for life-changing decisions ranging from college applications to visa…

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using…

Speech monologues recorded in naturalistic settings provide opportunities to characterize mental illness phenomenology and detect symptom exacerbation. Large language models (LLMs) offer new possibilities for automating this process, as…

Large Language Models (LLMs) have been demonstrating strong reasoning capability with their chain-of-thoughts (CoT), which are routinely used by humans to judge answer quality. This reliance creates a powerful yet fragile basis for trust.…

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claims to be iteratively refined over time. This process requires…

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

While deep learning makes significant achievements in Artificial Intelligence (AI), the lack of transparency has limited its broad application in various vertical domains. Explainability is not only a gateway between AI and real world, but…

Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…

We evaluate LLMs' language understanding capacities on simple inference tasks that most humans find trivial. Specifically, we target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii)…

Despite the recent advancement in large language models (LLMs) and their high performances across numerous benchmarks, recent research has unveiled that LLMs suffer from hallucinations and unfaithful reasoning. This work studies a specific…

Language model (LM) agents are increasingly used as autonomous decision-makers which need to actively gather information to guide their decisions. A crucial cognitive skill for such agents is the efficient exploration and understanding of…

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on…

Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve…

How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…

This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous…