The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations. The traditional setting limits each participant to one message at a time and requires constant human participation. This fails to reflect a natural conversational style and hinders the evaluation of dialogue agents based on Large Language Models (LLMs) in complex and prolonged interactions. This paper proposes X-Turing, which enhances the original test with a burst dialogue pattern, allowing more dynamic exchanges using consecutive messages. It further reduces human workload by iteratively generating dialogues that simulate the long-term interaction between the agent and a human to compose the majority of the test process. With the pseudo-dialogue history, the agent then engages in a shorter dialogue with a real human, which is paired with a human-human conversation on the same topic to be judged using questionnaires. We introduce the X-Turn Pass-Rate metric to assess the human likeness of LLMs across varying durations. While LLMs like GPT-4 initially perform well, achieving pass rates of 51.9% and 38.9% during 3 turns and 10 turns of dialogues respectively, their performance drops as the dialogue progresses, which underscores the difficulty in maintaining consistency in the long term.

LLM-based Interactive Drama is a novel AIbased dialogue scenario, where the user (i.e. the player) plays the role of a character in the story, has conversations with characters played by LLM agents, and experiences an unfolding story.This paper begins with understanding interactive drama from two aspects: Immersion-the player's feeling of being present in the story-and Agency-the player's ability to influence the story world.Both are crucial to creating an enjoyable interactive experience, while they have been underexplored in previous work.To enhance these two aspects, we first propose Playwriting-guided Generation, a novel method that helps LLMs craft dramatic stories with substantially improved structures and narrative quality.Additionally, we introduce Plot-based Reflection for LLM agents to refine their reactions to align with the player's intentions.Our evaluation relies on human judgment to assess the gains of our methods in terms of immersion and agency.

Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods.Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents.To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning.Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness.To address these challenges, we propose ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents.ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multimodal retrieval.To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains.Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach.Notably, ViDoRAG outperforms existing methods by over 10% on the competitive benchmark.The code is available at https: //github.com/Alibaba-NLP/ViDoRAG.

Backscatter communication has attracted significant attention due to its low power consumption and energy efficiency. Enabling concurrent backscatter allows multiple tags to operate simultaneously, and their data can be recovered from collided signals. This capability is crucial for enhancing management efficiency in smart logistics and mitigating multi-tag collisions in Internet-of-Things (IoT) scenarios where multiple tags work collaboratively. However, existing concurrent backscatter schemes are vulnerable to noise and asynchronous signals, causing limited performance. To address these challenges, we introduce Ortho-CodeA, a backscatter scheme that enables reliable concurrent backscatter communication despite high noise levels and asynchronous signals. The underlying concept is to take advantage of coding mechanisms to combat noise and employ time-shifted orthogonal codes to mitigate the effects of asynchronous signals. Specifically, we design a set of time-shifted orthogonal codes that maintain code orthogonality despite asynchronous signals. Built upon the designed codes, we develop a multi-tag decoding scheme to recover data from each tag. We theoretically analyze the feasibility of our scheme and validate its performance through extensive experimental simulations. The results demonstrate that Ortho-CodeA achieves a BER of about 0.0036% in the case of 7 tags with an SNR of 10 dB and a maximum time delay of$1 \,\mu \text{s}$.

Ontological knowledge, which comprises classes and properties and their relationships, is integral to world knowledge.It is significant to explore whether Pretrained Language Models (PLMs) know and understand such knowledge.However, existing PLM-probing studies focus mainly on factual knowledge, lacking a systematic probing of ontological knowledge.In this paper, we focus on probing whether PLMs store ontological knowledge and have a semantic understanding of the knowledge rather than rote memorization of the surface form.To probe whether PLMs know ontological knowledge, we investigate how well PLMs memorize: (1) types of entities; (2) hierarchical relationships among classes and properties, e.g., Person is a subclass of Animal and Member of Sports Team is a subproperty of Member of ; (3) domain and range constraints of properties, e.g., the subject of Member of Sports Team should be a Person and the object should be a Sports Team.To further probe whether PLMs truly understand ontological knowledge beyond memorization, we comprehensively study whether they can reliably perform logical reasoning with given knowledge according to ontological entailment rules.Our probing results show that PLMs can memorize certain ontological knowledge and utilize implicit knowledge in reasoning.However, both the memorizing and reasoning performances are less than perfect, indicating incomplete knowledge and understanding.

Open knowledge graph (KG) consists of (subject, relation, object) triples extracted from millions of raw text.The subject and object noun phrases and the relation in open KG have severe redundancy and ambiguity and need to be canonicalized.Existing datasets for open KG canonicalization only provide gold entitylevel canonicalization for noun phrases.In this paper, we present COMBO, a Complete Benchmark for Open KG canonicalization.Compared with existing datasets, we additionally provide gold canonicalization for relation phrases, gold ontology-level canonicalization for noun phrases, as well as source sentences from which triples are extracted.We also propose metrics for evaluating each type of canonicalization.On the COMBO dataset, we empirically compare previously proposed canonicalization methods as well as a few simple baseline methods based on pretrained language models.We find that properly encoding the phrases in a triple using pretrained language models results in better relation canonicalization and ontology-level canonicalization of the noun phrase.We release our dataset, baselines, and evaluation scripts at

The research on backscatter multiple access schemes has been an interesting topic. Existing schemes in the area of backscatter multiple access are not designed for specific applications, and leave out the contemplation of practical application requirements. In this paper, therefore, we present Ortho-CodeA, a backscatter multiple access scheme that targets indoor Internet of Things (IoT) applications (e.g., the smart home) and considers the practical application requirements. To implement Ortho-CodeA, we address several key challenges including imperfect time synchronization, high hardware complexity at receiver, and synchronizing multiple tags information in a low-power manner. We theoretically analyze the feasibility of our scheme and evaluate the performance of Ortho-CodeA through extensive simulations. The results show that Ortho-CodeA supports concurrent transmissions of up to 7 tags and achieves BER of 0 when SNR is greater or equal to 0 dB.

Many opportunistic routing (OR) schemes treat network nodes equally, neglecting the fact that the nodes close to the sink undertake more duties than the rest of the network nodes. Therefore, the nodes located at different positions should play different roles during the routing process. Moreover, considering various Quality-of-Service (QoS) requirements, the routing decision in OR is affected by multiple network attributes. The majority of these OR schemes fail to contemplate multiple network attributes while making routing decisions. To address the aforesaid issues, this paper presents a novel protocol that runs in three steps. First, each node defines aRouting Zone (RZ)to route packets toward the sink. Second, the nodes within RZ are prioritized based on the competency value obtained through a novel model that employs Modified Analytic Hierarchy Process (MAHP) and Fuzzy Logic techniques. Finally, one of the forwarders is selected as the final relay node after forwarders coordination. Through extensive experimental simulations, it is confirmed that FLORA achieves better performance compared to its counterparts in terms of energy consumption, overhead packets, waiting times, packet delivery ratio, and network lifetime.

Ultra-fine entity typing (UFET) aims to predict a wide range of type phrases that correctly describe the categories of a given entity mention in a sentence.Most recent works infer each entity type independently, ignoring the correlations between types, e.g., when an entity is inferred as a president, it should also be a politician and a leader.To this end, we use an undirected graphical model called pairwise conditional random field (PCRF) to formulate the UFET problem, in which the type variables are not only unarily influenced by the input but also pairwisely relate to all the other type variables.We use various modern backbones for entity typing to compute unary potentials, and derive pairwise potentials from type phrase representations that both capture prior semantic information and facilitate accelerated inference.We use mean-field variational inference for efficient type inference on very large type sets and unfold it as a neural network module to enable end-to-end training.Experiments on UFET show that the Neural-PCRF consistently outperforms its backbones with little cost and results in a competitive performance against crossencoder based SOTA while being thousands of times faster.We also find Neural-PCRF effective on a widely used fine-grained entity typing dataset with a smaller type set.We pack Neural-PCRF as a network module that can be plugged onto multi-label type classifiers with ease and release it in github.com/modelscope/ adaseq/examples/NPCRF.