Search

Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed bandit framework to learn user preferences in an online manner and have received great success in recent years. However, existing conversational bandit methods have several limitations. First, they only enable users to provide explicit binary feedback on the recommended items or categories, leading to ambiguity in interpretation. In practice, users are usually faced with more than one choice. Relative feedback, known for its informativeness, has gained increasing popularity in recommendation system design. Moreover, current contextual bandit methods mainly work under linear reward assumptions, ignoring practical non-linear reward structures in generalized linear models. Therefore, in this paper, we introduce relative feedback-based conversations into conversational recommendation systems through the integration of dueling bandits in generalized linear models (GLM) and propose a novel conversational dueling bandit algorithm called ConDuel. Theoretical analyses of regret upper bounds and empirical validations on synthetic and real-world data underscore ConDuel's efficacy. We also demonstrate the potential to extend our algorithm to multinomial logit bandits with theoretical and experimental guarantees, which further proves the applicability of the proposed framework.

Recommender systems present relevant contents to users and help content creators reach their target audience. The dual nature of these systems influences both users and creators: users' preferences are affected by the items they are recommended, while creators are incentivized to alter their contents such that it is recommended more frequently. We define a model, called user-creator feature dynamics, to capture the dual influences of recommender systems. We prove that a recommender system with dual influence is guaranteed to polarize, causing diversity loss in the system. We then investigate, both theoretically and empirically, approaches for mitigating polarization and promoting diversity in recommender systems. Unexpectedly, we find that common diversity-promoting approaches do not work in the presence of dual influence, while relevancy-optimizing methods like top-$k$ recommendation can prevent polarization and improve diversity of the system.

The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. However, collecting prompts that provide comprehensive coverage is both tedious and challenging, and often fails to include scenarios that LLMs need to improve on the most. In this paper, we investigate alignment through the lens of two-agent games, involving iterative interactions between an adversarial and a defensive agent. The adversarial agent's task at each step is to generate prompts that expose the weakness of the defensive agent. In return, the defensive agent seeks to improve its responses to these newly identified prompts it struggled with, based on feedback from the reward model. We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents. Experimental results in safety scenarios demonstrate that learning in such a competitive environment not only fully trains agents but also leads to policies with enhanced generalization capabilities for both adversarial and defensive agents., Comment: Our code is released at https://github.com/ruizheng20/gpo

Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training on new documents. However, they frequently face difficulties in extracting stored knowledge. Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM's ability to effectively acquire new knowledge from raw documents through self-teaching. Specifically, we develop a Self-Teaching strategy that augments the documents with a set of knowledge-intensive tasks created in a self-supervised manner, focusing on three crucial aspects: memorization, comprehension, and self-reflection. In addition, we introduce three Wiki-Newpages-2023-QA datasets to facilitate an in-depth analysis of an LLM's knowledge acquisition ability concerning memorization, extraction, and reasoning. Extensive experimental results on Llama2 family models reveal that Self-Tuning consistently exhibits superior performance across all knowledge acquisition tasks and excels in preserving previous knowledge., Comment: 30 pages

This paper aims to investigate the disparities in pedestrian crossing behaviors within static and dynamic crowds through experimental analysis. First, the crossing trajectories of pedestrians in various crowd environments were qualitatively observed. These trajectories have shown significant discrepancies and the phenomenon of cross-channel formation within static crowds was observed, a phenomenon similar to the evolution of human trails. To quantitatively assess these discrepancies, metrics of behavior patterns and swarm factor were introduced. Different behavioral patterns, including anticipation and reaction behaviors in pedestrian motion, were observed. Finally, through orthogonal velocity analysis, the variation trends of crossing motions within static and dynamic contexts were revealed., Comment: 12 pages, 11 figures

The recently developed affine frequency division multiplexing (AFDM) can achieve full diversity in doubly selective channels, providing a comprehensive sparse representation of the delay-Doppler domain channel. Thus, accurate channel estimation is feasible by using just one pilot symbol. However, traditional AFDM channel estimation schemes necessitate the use of guard intervals (GI) to mitigate data-pilot interference, leading to spectral efficiency degradation. In this paper, we propose a GI-free pilot-aided channel estimation algorithm for AFDM systems, which improves spectral efficiency significantly. To mitigate the interference between the pilot and data symbols caused by the absence of GI, we perform joint interference cancellation, channel estimation, and signal detection iterately. Simulation results show that the bit error rate (BER) performance of the proposed method can approach the ideal case with perfect channel estimation.

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable and sensitive to noise from various sources, e.g. human labeling errors, making the pipeline fragile. In this work, we improve the effectiveness of the reward model by introducing a penalty term on the reward, named as \textit{contrastive rewards}. %Contrastive rewards Our approach involves two steps: (1) an offline sampling step to obtain responses to prompts that serve as baseline calculation and (2) a contrastive reward calculated using the baseline responses and used in the Proximal Policy Optimization (PPO) step. We show that contrastive rewards enable the LLM to penalize reward uncertainty, improve robustness, encourage improvement over baselines, calibrate according to task difficulty, and reduce variance in PPO. We show empirically contrastive rewards can improve RLHF substantially, evaluated by both GPTs and humans, and our method consistently outperforms strong baselines.

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs). Over-optimization occurs when a reward model serves as an imperfect proxy for human preference, and RL-driven policy optimization erroneously exploits reward inaccuracies. In this paper, we begin by introducing a lightweight way to quantify uncertainties in rewards, relying solely on the last layer embeddings of the reward model, without the need for computationally expensive reward ensembles. AdvPO then addresses a distributionally robust optimization problem centred around the confidence interval of the reward model's predictions for policy improvement. Through comprehensive experiments on the Anthropic HH and TL;DR summarization datasets, we illustrate the efficacy of AdvPO in mitigating the overoptimization issue, consequently resulting in enhanced performance as evaluated through human-assisted evaluation.

Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e. "hallucinations", even when they hold relevant knowledge. To address these hallucinations, current approaches typically necessitate high-quality human factuality annotations. In this work, we explore Self-Alignment for Factuality, where we leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality. Specifically, we incorporate Self-Eval, a self-evaluation component, to prompt an LLM to validate the factuality of its own generated responses solely based on its internal knowledge. Additionally, we design Self-Knowledge Tuning (SK-Tuning) to augment the LLM's self-evaluation ability by improving the model's confidence estimation and calibration. We then utilize these self-annotated responses to fine-tune the model via Direct Preference Optimization algorithm. We show that the proposed self-alignment approach substantially enhances factual accuracy over Llama family models across three key knowledge-intensive tasks on TruthfulQA and BioGEN., Comment: 20 pages

Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. These approaches have been criticized for overgeneralizing the moral stances of a limited group of annotators and lacking explainability. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research. The theory-guided top-down framework can incorporate various moral theories. Our experiments demonstrate the effectiveness of the proposed framework on datasets derived from moral theories. Furthermore, we show the alignment between different moral theories and existing morality datasets. Our analysis exhibits the potential and flaws in existing resources (models and datasets) in developing explainable moral judgment-making systems.

Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. For instance, OpenAI devoted six months to iteratively aligning GPT-4 before its release [3]. However, a major challenge faced by practitioners is the lack of clear guidance on evaluating whether LLM outputs align with social norms, values, and regulations. This obstacle hinders systematic iteration and deployment of LLMs. To address this issue, this paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing LLM trustworthiness. The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Each major category is further divided into several sub-categories, resulting in a total of 29 sub-categories. Additionally, a subset of 8 sub-categories is selected for further investigation, where corresponding measurement studies are designed and conducted on several widely-used LLMs. The measurement results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness. However, the effectiveness of alignment varies across the different trustworthiness categories considered. This highlights the importance of conducting more fine-grained analyses, testing, and making continuous improvements on LLM alignment. By shedding light on these key dimensions of LLM trustworthiness, this paper aims to provide valuable insights and guidance to practitioners in the field. Understanding and addressing these concerns will be crucial in achieving reliable and ethically sound deployment of LLMs in various applications., Comment: Fixed several typos

Building end-to-end task bots and maintaining their integration with new functionalities using minimal human efforts is a long-standing challenge in dialog research. Recently large language models (LLMs) have demonstrated exceptional proficiency in conversational engagement and adherence to instructions across various downstream tasks. In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on LLMs. Utilizing the symbolic knowledge -- task schema, we instruct fixed LLMs to generate appropriate responses on novel tasks, circumventing the need for training data. Specifically, SGP-TOD comprises three components: a LLM for engaging with users, a DST Prompter to aid the LLM with dialog state tracking, which is then used to retrieve database items, and a Policy Prompter to elicit proper responses adhering to the provided dialog policy. Experimental results on Multiwoz, RADDLE and STAR datasets show that our training-free strategy SGP-TOD, without any task-specific data, yields state-of-the-art (SOTA) zero-shot performance, greatly surpasses the few-shot approaches. In a domain-extension setting, SGP-TOD aptly adapts to new functionalities by merely adding supplementary schema rules. We make our code and data publicly available., Comment: 21 pages, 13 figures

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as search engines, recommender systems, and etc. While the ground-truth logging policy, which generates the logged data, is usually unknown, previous work simply takes its estimated value in off-policy learning, ignoring both high bias and high variance resulted from such an estimator, especially on samples with small and inaccurately estimated logging probabilities. In this work, we explicitly model the uncertainty in the estimated logging policy and propose a Uncertainty-aware Inverse Propensity Score estimator (UIPS) for improved off-policy learning, with a theoretical convergence guarantee. Experiment results on synthetic and three real-world recommendation datasets demonstrate the advantageous sample efficiency of the proposed UIPS estimator against an extensive list of state-of-the-art baselines.

Recommendation systems aim to predict users' feedback on items not exposed to them. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic status of a user) that can affect both a user's exposure and feedback. Existing methods either (1) make untenable assumptions about these unmeasured variables or (2) directly infer latent confounders from users' exposure. However, they cannot guarantee the identification of counterfactual feedback, which can lead to biased predictions. In this work, we propose a novel method, i.e., identifiable deconfounder (iDCF), which leverages a set of proxy variables (e.g., observed user features) to resolve the aforementioned non-identification issue. The proposed iDCF is a general deconfounded recommendation framework that applies proximal causal inference to infer the unmeasured confounders and identify the counterfactual feedback with theoretical guarantees. Extensive experiments on various real-world and synthetic datasets verify the proposed method's effectiveness and robustness.

Accuracy and diversity have long been considered to be two conflicting goals for recommendations. We point out, however, that as the diversity is typically measured by certain pre-selected item attributes, e.g., category as the most popularly employed one, improved diversity can be achieved without sacrificing recommendation accuracy, as long as the diversification respects the user's preference about the pre-selected attributes. This calls for a fine-grained understanding of a user's preferences over items, where one needs to recognize the user's choice is driven by the quality of the item itself, or the pre-selected attributes of the item. In this work, we focus on diversity defined on item categories. We propose a general diversification framework agnostic to the choice of recommendation algorithms. Our solution disentangles the learnt user representation in the recommendation module into category-independent and category-dependent components to differentiate a user's preference over items from two orthogonal perspectives. Experimental results on three benchmark datasets and online A/B test demonstrate the effectiveness of our solution in improving both recommendation accuracy and diversity. In-depth analysis suggests that the improvement is due to our improved modeling of users' categorical preferences and refined ranking within item categories., Comment: Accepted to WSDM2023

Deep learning is applied to many complex tasks in the field of wireless communication, such as modulation recognition of spectrum waveforms, because of its convenience and efficiency. This leads to the problem of a malicious third party using a deep learning model to easily recognize the modulation format of the transmitted waveform. Some existing works address this problem directly using the concept of adversarial examples in the image domain without fully considering the characteristics of the waveform transmission in the physical world. Therefore, we propose a low-intercept waveform~(LIW) generation method that can reduce the probability of the modulation being recognized by a third party without affecting the reliable communication of the friendly party. Our LIW exhibits significant low-interception performance even in the physical hardware experiment, decreasing the accuracy of the state of the art model to approximately $15\%$ with small perturbations., Comment: 4 pages, 4 figures, published in 2021 34th General Assembly and Scientific Symposium of the International Union of Radio Science, URSI GASS 2021

End-to-end task bots are typically learned over a static and usually limited-size corpus. However, when deployed in dynamic, changing, and open environments to interact with users, task bots tend to fail when confronted with data that deviate from the training corpus, i.e., out-of-distribution samples. In this paper, we study the problem of automatically adapting task bots to changing environments by learning from human-bot interactions with minimum or zero human annotations. We propose SL-AGENT, a novel self-learning framework for building end-to-end task bots. SL-AGENT consists of a dialog model and a pre-trained reward model to predict the quality of an agent response. It enables task bots to automatically adapt to changing environments by learning from the unlabeled human-bot dialog logs accumulated after deployment via reinforcement learning with the incorporated reward model. Experimental results on four well-studied dialog tasks show the effectiveness of SL-AGENT to automatically adapt to changing environments, using both automatic and human evaluations. We will release code and data for further research.