As large language models (LLMs) become increasingly prevalent The widespread adoption of large language models (LLMs) in web in web services, effectively leveraging domain-specific knowledge services has profoundly impacted various domains, yet their application while ensuring privacy has become critical. Existing methods, such in specialized domains - especially those handling sensitive as retrieval-augmented generation (RAG) and differentially private data - faces significant hurdles. State-of-the-art LLMs, such as GPT-data synthesis, often compromise either the utility of domain knowledge 4 [29] and Gemini [41], are typically closed-source and owned by or the privacy of sensitive data, limiting their applicability large companies (referred to as servers). These models, trained on in specialized domains. To address these challenges, we propose extensive public datasets, frequently struggle to deliver accurate Llamdex, a novel framework that integrates privacy-preserving, results in specialized areas like healthcare and finance, where precision domain-specific models into LLMs. Our approach significantly enhances is crucial. For example, a misdiagnosis in medical contexts the accuracy of domain-specific tasks, achieving up to a can pose serious health risks, while erroneous financial forecasts 26% improvement compared to existing methods under the same can lead to substantial economic implications.

The rapid advancement of large language models (LLMs) has accelerated their application in reasoning, with strategic reasoning drawing increasing attention. To evaluate the strategic reasoning capabilities of LLMs, game theory, with its concise structure, has become the preferred approach for many researchers. However, current research typically focuses on a limited selection of games, resulting in low coverage of game types. Additionally, classic game scenarios carry risks of data leakage, and the benchmarks used often lack extensibility, rendering them inadequate for evaluating state-of-the-art models. Specifically, we incorporate all 144 game types summarized by the Robinson-Goforth topology of 2 2 games, which are constructed as classic games in our benchmark. Furthermore, we employ synthetic data generation techniques to create diverse, higher-quality game scenarios through topic guidance and human inspection for each classic game, which we refer to as story-based games. Lastly, to provide a sustainable evaluation framework adaptable to increasingly powerful LLMs, we treat the aforementioned games as atomic units and organize them into more complex forms through sequential, parallel, and nested structures. We conducted a comprehensive evaluation of mainstream LLMs, covering tests on rational reasoning, reasoning robustness, Theory-of-Mind capabilities, and reasoning in complex game forms. The results revealed that LLMs still have flaws in the accuracy and consistency of strategic reasoning processes, and their levels of mastery over Theory-of-Mind also vary. These achievements are largely attributed to LLMs' ability to assimilate vast amounts of knowledge during training, emerging with the capacity to organize information at a coarse level and link knowledge at a finegrained level through their internal representations (Min et al., 2023; Zhao et al., 2023). These core capabilities have driven the success of LLMs in numerous reasoning tasks, including mathematical reasoning (Hendrycks et al., 2021; Zhang et al., 2023), commonsense reasoning (Sap et al., 2019; Bisk et al., 2020), logical reasoning (Lei et al., 2023), and strategic reasoning (Lorè & Heydari, Work done during an internship at the University of Hong Kong. The dataset and evaluation codes will be available at https://github.com/PinkEx/TMGBench. Among these, strategic reasoning has attracted considerable attention due to its multi-agent nature and close association with social intelligence (Gandhi et al., 2023). Strategic reasoning refers to the cognitive process of anticipating, planning, and responding to others' actions to achieve specific objectives within competitive or cooperative contexts (Zhang et al., 2024a).

This study exposes the safety vulnerabilities of Large Language Models (LLMs) in multi-turn interactions, where malicious users can obscure harmful intents across several queries. We introduce ActorAttack, a novel multi-turn attack method inspired by actor-network theory, which models a network of semantically linked actors as attack clues to generate diverse and effective attack paths toward harmful targets. ActorAttack addresses two main challenges in multi-turn attacks: (1) concealing harmful intents by creating an innocuous conversation topic about the actor, and (2) uncovering diverse attack paths towards the same harmful target by leveraging LLMs' knowledge to specify the correlated actors as various attack clues. In this way, ActorAttack outperforms existing single-turn and multi-turn attack methods across advanced aligned LLMs, even for GPT-o1. We will publish a dataset called SafeMTData, which includes multi-turn adversarial prompts and safety alignment data, generated by ActorAttack. We demonstrate that models safety-tuned using our safety dataset are more robust to multi-turn attacks. Code is available at https://github.com/renqibing/ActorAttack.

This paper presents an improved framework for character-aware audio-visual subtitling in TV shows. Our approach integrates speech recognition, speaker diarisation, and character recognition, utilising both audio and visual cues. This holistic solution addresses what is said, when it's said, and who is speaking, providing a more comprehensive and accurate character-aware subtitling for TV shows. Our approach brings improvements on two fronts: first, we show that audio-visual synchronisation can be used to pick out the talking face amongst others present in a video clip, and assign an identity to the corresponding speech segment. This audio-visual approach improves recognition accuracy and yield over current methods. Second, we show that the speaker of short segments can be determined by using the temporal context of the dialogue within a scene. We propose an approach using local voice embeddings of the audio, and large language model reasoning on the text transcription. This overcomes a limitation of existing methods that they are unable to accurately assign speakers to short temporal segments. We validate the method on a dataset with 12 TV shows, demonstrating superior performance in speaker diarisation and character recognition accuracy compared to existing approaches. Project page : https://www.robots.ox.ac.uk/~vgg/research/llr-context/

Closed-source large language models deliver strong performance but have limited downstream customizability. Semi-open models, combining both closed-source and public layers, were introduced to improve customizability. However, parameters in the closed-source layers are found vulnerable to recovery attacks. In this paper, we explore the design of semi-open models with fewer closed-source layers, aiming to increase customizability while ensuring resilience to recovery attacks. We analyze the contribution of closed-source layer to the overall resilience and theoretically prove that in a deep transformer-based model, there exists a transition layer such that even small recovery errors in layers before this layer can lead to recovery failure. SCARA employs a fine-tuning-free metric to estimate the maximum number of layers that can be publicly accessible for customization. We apply it to five models (1.3B to 70B parameters) to construct semi-open models, validating their customizability on six downstream tasks and assessing their resilience against various recovery attacks on sixteen benchmarks. We compare SCARA to baselines and observe that it generally improves downstream customization performance and offers similar resilience with over 10 times fewer closed-source parameters. We empirically investigate the existence of transition layers, analyze the effectiveness of our scheme and finally discuss its limitations. Open-sourcing more parameters and structure details apparently enhances downstream customizability. However, Zanella-Beguelin et al. (2021) showed that semi-open LLMs with only a few closed-source parameters are vulnerable to model recovery attacks. Recovery attackers query the closed-source module and then train a new module that imitates its functionality. This can lead to the full replication and theft of closed-source modules (Solaiman, 2023). Recovery attackers targeting fully closed-source models seek to fine-tune a new model that precisely replicates the closed-source model (Tamber et al., 2024; Dubiński et al., 2024). In contrast, attackers in semi-open settings are not required to exactly replicate the closed-source module. Instead, they can fine-tune the closed-source module alongside the public module to reconstruct the overall functionality. While open-sourcing more layers enhances downstream flexibility, it also facilitates easier replication.

Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external traceable resources for response generation. The essence of RAG in combating the hallucination issue lies in accurately attributing claims in responses to the corresponding retrieved documents. However, most of existing works focus on improving the quality of generated responses from the LLM, while largely overlooked its ability to attribute sources accurately. In this study, we conduct a systematic analysis about the capabilities of LLMs in generating citations within response generation, and further introduce a novel method to enhance their citation generation abilities. Specifically, we evaluate both the correctness and citation quality for seven widely-used LLMs on two benchmark datasets. Meanwhile, we introduce new citation evaluation metrics to eliminate the over-penalization of unnecessary and excessive citations in existing metrics. Furthermore, we propose a Generate-then-Refine method that completes relevant citations and removes irrelevant ones without altering the response text. The results on WebGLM-QA, ASQA and ELI5 datasets show that our method substantially improves the quality of citations in responses generated by LLMs.

One of the main issues with the current In the current era of Large Language Models (LLMs), with retrieval approaches using Retrieval-Augmented Generation an abundance of data, there is always a tricky question to is hallucination, where the model gives out irrelevant, be addressed: Is providing an abundance of data enough to incorrect, and unreal responses. By incorporating subsumptions solve complex tasks? The majority of modern-day models in the prompt, we ensure hallucination is minimized are fundamentally probabilistic, which though highly powerful and the response of the Language Model is more contextually in its way, gives the model only an uncertain output and factually intact. Section 4 presents key insights that cannot be reasoned out. This uncertainty is of 2 from our experimentation with ontologies in the medical domain, types, epistemic (EU) and aleatoric (AU), where the former demonstrating how our methodology could be used is also called reducible uncertainty, caused due to the lack of for quicker training and reducing hallucinations in LLMs.

In customer contact centers, human agents often struggle with long average handling times (AHT) due to the need to manually interpret queries and retrieve relevant knowledge base (KB) articles. While retrieval augmented generation (RAG) systems using large language models (LLMs) have been widely adopted in industry to assist with such tasks, RAG faces challenges in real-time conversations, such as inaccurate query formulation and redundant retrieval of frequently asked questions (FAQs). To address these limitations, we propose a decision support system that can look beyond RAG by first identifying customer questions in real time. If the query matches an FAQ, the system retrieves the answer directly from the FAQ database; otherwise, it generates answers via RAG. Our approach reduces reliance on manual queries, providing responses to agents within 2 seconds. Deployed in AI-powered human-agent assist solution at Minerva CQ, this system improves efficiency, reduces AHT, and lowers operational costs. We also introduce an automated LLM-agentic workflow to identify FAQs from historical transcripts when no predefined FAQs exist.

Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate generation modules (a.k.a. generators). As such, generators' performance largely depends on the effectiveness and efficiency of retrievers. However, the retrieval paradigm that we design and use remains flat, which treats the retrieval procedures as a one-off deal with constant granularity. Despite effectiveness, we argue that they suffer from two limitations: (1) flat retrieval exerts a significant burden on one retriever; (2) constant granularity limits the ceiling of retrieval performance. In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. Specifically, FunnelRAG establishes a progressive retrieval pipeline by collaborating coarse-to-fine granularity, large-to-small quantity, and low-to-high capacity, which can relieve the burden on one retriever and also promote the ceiling of retrieval performance. Extensive experiments manifest that FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent.

While large language models (LLMs) have shown impressive capabilities across a wide range of domains, they still encounter significant challenges in reasoning tasks that require gathering evidence over multiple turns and drawing logical conclusions from this evidence. These challenges present significant obstacles for LLM chat user interfaces, which rely on multi-turn interactions to facilitate effective collaboration. This limitation leads to real-world issues; for example, service chatbots must gather necessary information from customers over multiple turns to diagnose and resolve problems effectively. Despite the multi-turn nature of many real-world LLM use cases, most existing benchmarks rely on carefully curated single-turn tests, which often blur the line between memorization and genuine reasoning. To address this, we introduce the Wason Inductive Logic Test (WILT), a simple yet challenging multi-turn reasoning benchmark designed to resist memorization. WILT is inspired by the Wason 2-4-6 task (Wason, 1960), where participants must infer a basic boolean function involving three variables (e.g., x < y < z) by proposing test cases (such as (2, 4, 6)). In WILT, each test starts from a clean slate, with only the initial instructions provided, preventing models from relying on pre-learned responses. Over several turns, models must interact with the environment by suggesting test cases to narrow the possible hypotheses and ultimately infer the hidden function based on the outcomes. Our findings reveal that LLMs struggle with this task, exhibiting distinct strengths and weaknesses: some are better at narrowing down the hypothesis space by proposing valuable test cases, while others are more adept at deducing the hidden function from observed cases. Despite these variations, the best-performing model achieves only 28% accuracy, highlighting a significant gap in LLM performance on complex multi-turn reasoning tasks. Large language models (LLMs) powered by the transformer architecture (Vaswani, 2017) have enabled a new computing paradigm driven by natural language. These models are increasingly integrated into day-to-day life beyond the machine learning research space, where they help many people with common tasks. These models interact with users through multi-turn conversations, a capability of next-token-prediction models bolstered via instruction-tuning (Mishra et al., 2021) and alignment post-training phases (Ouyang et al., 2022).