Search for: All records

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that \method outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9.01% across five diverse personalization tasks in the LaMP benchmark. 

Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-modifying ME and parameter-preserving ME (integrating extra modules while preserving original parameters). Regrettably, previous studies on ME evaluation have two critical limitations: (i) evaluating LLMs with single edit only, neglecting the need for continuous editing, and (ii) evaluations focusing solely on basic factual triples, overlooking broader LLM capabilities like logical reasoning and reading understanding. This study addresses these limitations with contributions threefold: (i) We explore how ME affects a wide range of fundamental capabilities of LLMs under sequential editing. Experimental results reveal an intriguing phenomenon: Most parameter-modifying ME consistently degrade performance across all tasks after a few sequential edits. In contrast, parameter-preserving ME effectively maintains LLMs’ fundamental capabilities but struggles to accurately recall edited knowledge presented in a different format. (ii) We extend our evaluation to different editing settings, such as layers to edit, model size, instruction tuning, etc. Experimental findings indicate several strategies that can potentially mitigate the adverse effects of ME. (iii) We further explain why parameter-modifying damages LLMs from three dimensions: parameter changes after editing, language modeling capability, and the in-context learning capability. Our in-depth study advocates more careful use of ME in real-world scenarios. 

Despite their vast capabilities, Large Language Models (LLMs) often struggle with generating reliable outputs, frequently producing high-confidence inaccuracies known as hallucinations. Addressing this challenge, our research introduces InternalInspector, a novel framework designed to enhance confidence estimation in LLMs by leveraging contrastive learning on internal states including attention states, feed-forward states, and activation states of all layers. Unlike existing methods that primarily focus on the final activation state, InternalInspector conducts a comprehensive analysis across all internal states of every layer to accurately identify both correct and incorrect prediction processes. By benchmarking InternalInspector against existing confidence estimation methods across various natural language understanding and generation tasks, including factual question answering, commonsense reasoning, and reading comprehension, InternalInspector achieves significantly higher accuracy in aligning the estimated confidence scores with the correctness of the LLM’s predictions and lower calibration error. Furthermore, InternalInspector excels at HaluEval, a hallucination detection benchmark, outperforming other internal-based confidence estimation methods in this task. 

Taxonomies, which organize knowledge hierarchically, support various practical web applications such as product navigation in online shopping and user profle tagging on social platforms. Given the continued and rapid emergence of new entities, maintaining a comprehensive taxonomy in a timely manner through human annotation is prohibitively expensive. Therefore, expanding a taxonomy automatically with new entities is essential. Most existing methods for expanding taxonomies encode entities into vector embeddings (i.e., single points). However, we argue that vectors are insufcient to model the “is-a” hierarchy in taxonomy (asymmetrical relation), because two points can only represent pairwise similarity (symmetrical relation). To this end, we propose to project taxonomy entities into boxes (i.e., hyperrectangles). Two boxes can be "contained", "disjoint" and "intersecting", thus naturally representing an asymmetrical taxonomic hierarchy. Upon box embeddings, we propose a novel model BoxTaxo for taxonomy expansion. The core of BoxTaxo is to learn boxes for entities to capture their child-parent hierarchies. To achieve this, BoxTaxo optimizes the box embeddings from a joint view of geometry and probability. BoxTaxo also ofers an easy and natural way for inference: examine whether the box of a given new entity is fully enclosed inside the box of a candidate parent from the existing taxonomy. Extensive experiments on two benchmarks demonstrate the efectiveness of BoxTaxo compared to vector based models. 

The Keck Planet Finder (KPF) is a fiber-fed, high-resolution, high-stability spectrometer in development at the UC Berkeley Space Sciences Laboratory for the W.M. Keck Observatory. KPF is designed to characterize exoplanets via Doppler spectroscopy with a goal of a single measurement precision of 0.3 m s-1 or better, however its resolution and stability will enable a wide variety of astrophysical pursuits. Here we provide post-preliminary design review design updates for several subsystems, including: the main spectrometer, the fabrication of the Zerodur optical bench; the data reduction pipeline; fiber agitator; fiber cable design; fiber scrambler; VPH testing results and the exposure meter.