Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

/in /by

We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.

Read more

Dynamic Causal Discovery in Imitation Learning

/in /by

Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret control policies learned by the agent. Difficulties mainly come from two aspects: 1) agents in imitation learning are usually implemented as deep neural networks, which are black-box models and lack interpretability; 2) the latent causal mechanism behind agents’ decisions may vary along the trajectory, rather than staying static throughout time steps. To increase transparency and offer better interpretability of the neural agent, we propose to expose its captured knowledge in the form of a directed acyclic causal graph, with nodes being action and state variables and edges denoting the causal relations behind predictions. Furthermore, we design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. Concretely, we conduct causal discovery from the perspective of Granger causality and propose a self-explainable imitation learning framework, CAIL. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner. After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed CAIL in learning the dynamic causal graphs for understanding the decision-making of imitation learning meanwhilemaintaining high prediction accuracy.

Read more

Self-Consistent Decoding for More Factual Open Responses

/in /by

Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this work, we extend the idea to open response generation, by integrating voting into the decoding method. Each output sentence is selected from among multiple samples, conditioning on the previous selections, based on a simple token overlap score. We compare this “Sample & Select” method to greedy decoding, beam search, nucleus sampling, and the recently introduced hallucination avoiding decoders of DoLa, P-CRR, and S-CRR. We show that Sample & Select improves factuality by a 30% relative margin against these decoders in NLI-based evaluation on the subsets of CNN/DM and XSum used in the FRANK benchmark, while maintaining comparable ROUGE-1 F1 scores against reference summaries. We collect human verifications of the generated summaries, confirming the factual superiority of our method.

Read more

Distributed Fiber Optic Sensing for Fault Localization Caused by Fallen Tree Using Physics-informed ResNet

/in /by

Falling trees or their limbs can cause power lines to break or sag, sometimes resulting in devastating wildfires. Conventional protections such as circuit breakers, overcurrent relays and automatic circuit reclosers may clear short circuits caused by tree contact, but they may not detect cases where the conductors remain intact or a conducting path is not sufficient to create a full short circuit. In this paper, we introduce a novel, non-intrusive monitoring technique that detects and locates fallen trees, even if a short circuit is not triggered. This method employs distributed fiber optic sensing (DFOS) to detect vibrations along the power distribution line where corresponding fiber cables are installed. A physics-informed ResNet model is then utilized to interpret this information and accurately locate fallen trees, which sets it apart from traditional black-box predictions of machine learning algorithms. Our real-scale lab tests demonstrate highly accurate and reliable fallen tree detection and localization.

Read more

Field Trial of Coexistence and Simultaneous Switching of Real-Time Fiber Sensing and Coherent 400 GbE in a Dense Urban Environment

/in /by

Recent advances in optical fiber sensing have enabled telecom network operators to monitor their fiber infrastructure while generating new revenue in various application scenarios, including data center interconnect, public safety, smart cities, and seismic monitoring. However, given the high utilization of fiber networks for data transmission, it is undesirable to allocate dedicated fiber strands solely for sensing purposes. Therefore, it is crucial to ensure the reliable coexistence of fiber sensing and communication signals that co-propagate on the same fiber. In this paper, we conduct field trials in a reconfigurable optical add-drop multiplexer (ROADM) network enabled by the PAWR COSMOS testbed, utilizing metro area fibers in Manhattan, New York City. We verify the coexistence of real-time constant-amplitude distributed acoustic sensing (DAS), coherent 400 GbE, and analog radio-over-fiber (ARoF) signals. Measurement results obtained from the field trial demonstrate that the quality of transmission (QoT) of the coherent 400 GbE signal remains unaffected during co-propagation with DAS and ARoF signals in adjacent dense wavelength-division multiplexing (DWDM) channels. In addition, we present a use case of this coexistence system supporting preemptive DAS-informed optical path switching before link failure.

Read more

Fast WDM Provisioning With Minimum Probe Signals: The First Field Experiments For DC Exchanges

/in /by

There are increasing requirements for data center interconnection (DCI) services, which use fiber to connect any DC distributed in a metro area and quickly establish high-capacity optical paths between cloud services and mobile edge computing and the users. In such networks, coherent transceivers with various optical frequency ranges, modulators, and modulation formats installed at each connection point must be used to meet service requirements such as fast-varying traffic requests between user computing resources. This requires technologyand architectures that enable users and DCI operators to cooperate to achieve fast provisioning of WDM links and flexible route switching in a short time, independent of the transceiver’s implementation and characteristics. We propose an approach to estimate the end-to-end (EtE) generalized signal-to-noise ratio (GSNR) accurately in a short time, not by measuring the GSNR at the operational route and wavelength for the EtE optical path but by simply applying a quality of transmission probe channel link by link, at a wavelength/modulation-formatconvenient for measurement. Assuming connections between transceivers of various frequency ranges, modulators, and modulation formats, we propose a device software architecture in which the DCI operator optimizes the transmission mode between user transceivers with high accuracy using only common parameters such as the bit error rate. In this paper, we first implement software libraries for fast WDM provisioning and experimentally build different routes to verify the accuracy of this approach. For the operational EtE GSNR measurements, theaccuracy estimated from the sum of the measurements for each link was 0.6 dB, and the wavelength-dependent error was about 0.2 dB. Then, using field fibers deployed in the NSF COSMOS testbed, a Linux-based transmission device software architecture, and transceivers with different optical frequency ranges, modulators, andmodulation formats, the fast WDM provisioning of an optical path was completed within 6 min.

Read more

A system-on-chip microwave photonic processor solves dynamic RF interference in real-time with femtosecond latency

/in /by

Radio-frequency interference is a growing concern as wireless technology advances, with potentially life-threatening consequences like interference between radar altimeters and 5?G cellular networks. Mobile transceivers mix signals with varying ratios over time, posing challenges for conventional digital signal processing (DSP) due to its high latency. These challenges will worsen as future wireless technologies adopt higher carrier frequencies and data rates. However, conventional DSPs, already on the brink of their clock frequency limit, are expected to offer only marginal speed advancements. This paper introduces a photonic processor to address dynamic interference through blind source separation (BSS). Our system-on-chip processor employs a fully integrated photonic signal pathway in the analogue domain, enabling rapid demixing of received mixtures and recovering the signal-of-interest in under 15 picoseconds. This reduction in latency surpasses electronic counterparts by more than three orders of magnitude. To complement the photonic processor, electronic peripherals based on field-programmable gate array (FPGA) assess the effectiveness of demixing and continuously update demixing weights at a rate of up to 305?Hz. This compact setup features precise dithering weight control, impedance-controlled circuit board and optical fibre packaging, suitable for handheld and mobile scenarios. We experimentally demonstrate the processor’s ability to suppress transmission errors and maintain signal-to-noise ratios in two scenarios, radar altimeters and mobile communications. This work pioneers the real-time adaptability of integrated silicon photonics, enabling online learning and weight adjustments, and showcasing practical operational applications for photonic processing.

Read more

Enabling Cooperative Hybrid Beamforming in TDD-based Distributed MIMO Systems

/in /by

Distributed massive MIMO networks are envisioned to realize cooperative multi-point transmission in next-generation wireless systems. For efficient cooperative hybrid beamforming, the cluster of access points (APs) needs to obtain precise estimates of the uplink channel to perform reliable downlink precoding. However, due to the radio frequency (RF) impairments between the transceivers at the two en-points of the wireless channel, full channel reciprocity does not hold which results in performance degradation in the cooperative hybrid beamforming (CHBF) unless a suitable reciprocity calibration mechanism is in place. We propose a two-step approach to calibrate any two hybrid nodes in the distributed MIMO system. We then present and utilize the novel concept of reciprocal tandem to propose a low-complexity approach for jointly calibrating the cluster of APs and estimating the downlink channel. Finally, we validate our calibration technique’s effectiveness through numerical simulation.

Read more

Differentiable JPEG: The Devil is in The Details

/in /by

JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several differentiable approximations of JPEG have recently been proposed to address this issue. This paper conducts a comprehensive review of existing diff. JPEG approaches and identifies critical details that have been missed by previous methods. To this end, we propose a novel diff. JPEG approach, overcoming previous limitations. Our approach is differentiable w.r.t. the input image, the JPEG quality, the quantization tables, and the color conversion parameters. We evaluate the forward and backward performance of our diff. JPEG approach against existing methods. Additionally, extensive ablations are performed to evaluate crucial design choices. Our proposed diff. JPEG resembles the (non-diff.) reference implementation best, significantly surpassing the recent-best diff. approach by 3.47dB (PSNR) on average. For strong compression rates, we can even improve PSNR by 9.51dB. Strong adversarial attack results are yielded by our diff. JPEG, demonstrating the effective gradient approximation. Our code is available at https://github.com/necla-ml/Diff-JPEG.

Read more

Prompt-based Domain Discrimination for Multi-source Time Series Domain Adaptation

/in /by

Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous domain adaptation techniques proposed to tackle this complex problem, their primary focus has been on the common representations of time series data. This concentration might inadvertently lead to the oversight of valuable domain-specific information originating from different source domains. To bridge this gap, we introduce POND, a novel prompt-based deep learning model designed explicitly for multi-source time series domain adaptation. POND is tailored to address significant challenges, notably: 1) The unavailability of a quantitative relationship between meta-data information and time series distributions, and 2) The dearth of exploration into extracting domain specific meta-data information. In this paper, we present an instance-level prompt generator and afidelity loss mechanism to facilitate the faithful learning of meta-data information. Additionally, we propose a domain discrimination technique to discern domain-specific meta-data information from multiple source domains. Our approach involves a simple yet effective meta-learning algorithm to optimize the objective efficiently. Furthermore, we augment the model’s performance by incorporating the Mixture of Expert (MoE) technique. The efficacy and robustness of our proposed POND model are extensively validated through experiments across 50 scenarios encompassing five datasets, which demonstrates that our proposed POND model outperforms the state-of the-art methods by up to 66% on the F1-score.

Read more