As semiconductor technology node advances, the number of parameters in the modern device compact model increases drastically. Manual extraction of these model parameters becomes not only tedious but also impossible, and the automatic method is strongly desired. Traditional black-box optimization suffers from poor scalability due to the curse of dimensionality, while deep learning–based methods typically require large amounts of training data. To address these challenges, we propose CDRPE: a combined deep learning and self-attention enhanced reinforcement learning framework for automatically extracting a large set of DCM parameters across multiple electrical characteristics. The framework leverages a pre-trained multilayer perceptron to initialize core parameters, incorporates device physics knowledge to guide the search, and employs a self-attention–enhanced RL agent for efficient exploration in high-dimensional parameter spaces. Experimental results on BSIM4, BSIMSOI, and BSIMCMG demonstrate that CDRPE can automatically extract 100 parameters with root-mean-square error below 5% relative to TCAD and silicon data. Compared with existing methods, the proposed framework achieves a 7.7x speed up. Moreover, the generated models show good convergence in both digital and analog circuit simulations, exhibiting the potential of this framework for future practical applications.

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires prohibitively large datasets for new ad-hoc tasks. We argue that it is instead possible to align an LLM to a specific setting by leveraging a very small number ($<10$) of demonstrations as feedback. Our method, Demonstration ITerated Task Optimization (DITTO), directly aligns language model outputs to a user's demonstrated behaviors. Derived using ideas from online imitation learning, DITTO cheaply generates online comparison data by treating users' demonstrations as preferred over output from the LLM and its intermediate checkpoints. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts. Additionally, we conduct a user study soliciting a range of demonstrations from participants ($N=16$). Across our benchmarks and user study, we find that win-rates for DITTO outperform few-shot prompting, supervised fine-tuning, and other self-play methods by an average of 19\% points. By using demonstrations as feedback directly, DITTO offers a novel method for effective customization of LLMs.

While language model (LM)-powered chatbots and generative search engines excel at answering concrete queries, discovering information in the terrain of unknown unknowns remains challenging for users.To emulate the common educational scenario where children/students learn by listening to and participating in conversations with their parents/teachers, we create Collaborative STORM (Co-STORM). 1 Unlike QA systems that require users to ask all the questions, Co-STORM lets users observe and occasionally steer the discourse among several LM agents.The agents ask questions on the user's behalf, allowing the user to discover unknown unknowns serendipitously.To facilitate user interaction, Co-STORM assists users in tracking the discourse by organizing the uncovered information into a dynamic mind map, ultimately generating a comprehensive report as takeaways.For automatic evaluation, we construct the WildSeek dataset by collecting real information-seeking records with user goals.Co-STORM outperforms baseline methods on both discourse trace and report quality.In a further human evaluation 2 , 70% of participants prefer Co-STORM over a search engine, and 78% favor it over a RAG (Retrieval Augmented Generation) chatbot.

Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is provided at test time. Predicting the task-id for each test sample is a challenging problem. An emerging theory-guided approach (called TIL+OOD) is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with catastrophic forgetting. The model for each task is an out-of-distribution (OOD) detector rather than a conventional classifier. The OOD detector can perform both within-task (in-distribution (IND)) class prediction and OOD detection. The OOD detection capability is the key to task-id prediction during inference. However, this paper argues that using a traditional OOD detector for task-id prediction is sub-optimal because additional information (e.g., the replay data and the learned tasks) available in CIL can be exploited to design a better and principled method for task-id prediction. We call the new method TPL (Task-id Prediction based on Likelihood Ratio). TPL markedly outperforms strong CIL baselines and has negligible catastrophic forgetting. The code of TPL is publicly available at https://github.com/linhaowei1/TPL.

Yijia Shao, Yucheng Jiang, Theodore Kanell, Peter Xu, Omar Khattab, Monica Lam. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy norms becomes increasingly critical. However, quantifying the privacy norm awareness of LMs and the emerging privacy risk in LM-mediated communication is challenging due to (1) the contextual and long-tailed nature of privacy-sensitive cases, and (2) the lack of evaluation approaches that capture realistic application scenarios. To address these challenges, we propose PrivacyLens, a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories, enabling multi-level evaluation of privacy leakage in LM agents' actions. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. Using this dataset, we reveal a discrepancy between LM performance in answering probing questions and their actual behavior when executing user instructions in an agent setup. State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions. We also demonstrate the dynamic nature of PrivacyLens by extending each seed into multiple trajectories to red-team LM privacy leakage risk. Dataset and code are available at https://github.com/SALT-NLP/PrivacyLens.

Commonsense reasoning is omnipresent in human communications and thus is an important feature for open-domain dialogue systems.However, evaluating commonsense in dialogue systems is still an open challenge.We take the first step by focusing on event commonsense that considers events and their relations, and is crucial in both dialogues and general commonsense reasoning.We propose AC-CENT, an event commonsense evaluation metric empowered by commonsense knowledge bases (CSKBs).ACCENT first extracts eventrelation tuples from a dialogue, and then evaluates the response by scoring the tuples in terms of their compatibility with the CSKB.To evaluate ACCENT, we construct the first public event commonsense evaluation dataset for open-domain dialogues.Our experiments show that ACCENT is an efficient metric for event commonsense evaluation, which achieves higher correlations with human judgments than existing baselines.

Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.Adapting or posttraining an LM using an unlabeled domain corpus can produce even better performance for end-tasks in the domain.This paper proposes the problem of continually extending an LM by incrementally post-train the LM with a sequence of unlabeled domain corpora to expand its knowledge without forgetting its previous skills.The goal is to improve the few-shot end-task learning in these domains.The resulting system is called CPT (Continual Post-Training), which to our knowledge, is the first continual post-training system.Experimental results verify its effectiveness.

Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that endtasks in the domain can give improved performances.However, existing DA-training methods are in some sense blind as they do not explicitly identify what knowledge in the LM should be preserved and what should be changed by the domain corpus.This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge.Experimental results will demonstrate the effectiveness of the proposed approach.1

Online forms are widely used to collect data from human and have a multi-billion market.Many software products provide online services for creating semi-structured forms where questions and descriptions are organized by predefined structures.However, the design and creation process of forms is still tedious and requires expert knowledge.To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion).For model training and evaluation, we collect the first public online form dataset with 62K online forms.Experiment results show that FormLM significantly outperforms general-purpose language models on all tasks, with an improvement by 4.71 on Question Recommendation and 10.6 on Block Type Suggestion in terms of ROUGE-1 and Macro-F1, respectively.