Related papers: Every Language Model Has a Forgery-Resistant Signa…

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection…

To determine the safety of large language models (LLMs), AI developers must be able to assess their dangerous capabilities. But simple prompting strategies often fail to elicit an LLM's full capabilities. One way to elicit capabilities more…

Quantitative risk assessment in high-stakes domains relies on structured expert elicitation to estimate unobservable properties. The gold standard - the Delphi method - produces calibrated, auditable judgments but requires months of…

Fragment-based shape signature techniques have proven to be powerful tools for computer-aided drug design. They allow scientists to search for target molecules with some similarity to a known active compound. They do not require reference…

Steganography embeds secret messages in seemingly innocuous carriers for covert communication under surveillance. Current Provably Secure Steganography (PSS) schemes based on language models can guarantee computational indistinguishability…

The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into data and model biases, as well as potential risks. To this end,…

Although large language models (LLMs) have achieved great success in vast real-world applications, their vulnerabilities towards noisy inputs have significantly limited their uses, especially in high-stake environments. In these contexts,…

Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To…

Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence…

We introduce benchmark signatures to characterize the capacity demands of LLM benchmarks and their overlaps. Signatures are sets of salient tokens from in-the-wild corpora whose model token perplexity, reflecting training exposure, predicts…

Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies…

Detecting design pattern instances in unfamiliar codebases remains a challenging yet essential task for improving software quality and maintainability. Traditional static analysis tools often struggle with the complexity, variability, and…

Language development experts need tools that can automatically identify languages from fluent, conversational speech, and provide reliable estimates of usage rates at the level of an individual recording. However, language identification…

Digital fingerprinting is a framework for marking media files, such as images, music, or movies, with user-specific signatures to deter illegal distribution. Multiple users can collude to produce a forgery that can potentially overcome a…

Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases,…

Gesture and signature passwords are two-dimensional figures created by drawing on the surface of a touchscreen with one or more fingers. Prior results about their security have used resilience to either shoulder surfing, a human observation…

Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully -- and lie detection -- classifying whether a…

Sign languages are visual languages which convey information by signers' handshape, facial expression, body movement, and so forth. Due to the inherent restriction of combinations of these visual ingredients, there exist a significant…

Although good encryption functions are probabilistic, most symbolic models do not capture this aspect explicitly. A typical solution, recently used to prove the soundness of such models with respect to computational ones, is to explicitly…

Effective communication is vital in healthcare, especially across language barriers, where non-verbal cues and gestures are critical. This paper presents a privacy-preserving vision-language framework for medical interpreter robots that…