55 accepted papers
Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits and limitations through a tractable graph-based abstraction,…
*Debate*, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight. However, debate faces a fundamental tension: models are incentivized to be persuasive to the judge, which may not always align with epistemic honesty. In this work, we propose an alternative para…
Safety alignment of Large Language Models (LLMs) is extremely fragile, fine-tuning on small number of benign samples can erase safety behaviors learned from millions of preference examples. Existing studies attempt to explain this phenomenon by comparing parameters and hidden states before and after…
Language models (LMs) judges are widely used to evaluate the quality of LM outputs. Despite many advantages, LM judges display concerning biases that can impair their integrity in evaluations. One such bias is self-preference: LM judges preferring their own answers over those produced by other LMs o
The increasing situational awareness of language models raises safety concerns: models might be aware when they are evaluated, and adjust their behavior to evade monitoring and resist modification, e.g., pretending to be aligned only in evaluation. This \emph{alignment faking} behavior is often inte…
Proprietary models are increasingly dominating the race for ever-larger language models. Can open-source, smaller models remain competitive across a broad range of tasks? In this paper, we present the Avengers---a lightweight framework that leverages the collective intelligence of these smaller mod
To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or evaluate (ChatbotArena) on what users prefer, assuming this reflects what helps them. We test this with Planorama: an int
As AI grows more powerful, it will increasingly shape how we understand the world. But with this influence comes the risk of amplifying misinformation and deepening social divides—especially on consequential topics where factual accuracy directly impacts well-being. Scalable Oversight aims to ensure…
As large language models (LLMs) grow more powerful, they also become more difficult to trust. They could be either aligned with human intentions, or exhibit "subversive misalignment" -- introducing subtle errors that bypass safety checks. Although individual errors may not immediately cause harm, ea…
Constrained by the cost and ethical concerns of involving real seekers in AI-driven mental health, researchers develop LLM-based conversational agents (CAs) with tailored configurations, such as profiles, symptoms, and scenarios, to simulate seekers. While these efforts advance AI in mental health,…
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing humans that they are right even when they are wron…
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data. This reliance sets a ceiling on LLM performance and is particularl
Current conversational recommendation systems focus predominantly on text. However, real-world recommendation settings are generally multimodal, causing a significant gap between existing research and practical applications. To address this issue, we propose Muse, the first multimodal conversational…
Existing visual perception systems focus on region-level segmentation in single-turn dialogues, relying on complex and explicit query instructions. Such systems cannot reason at the pixel level and comprehend dynamic user intent that changes over interaction. Our work tackles this issue by introduci…
Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even expert researchers can only acquire through substantial experi…
Question answering (QA)—giving correct answers to questions—is a popular task, but we test **reverse question answering (RQA)**: for an input answer, give a question with that answer. Past work tests QA and RQA separately, but we test them jointly, comparing their difficulty, aiding benchmark design…
Fine-tuning is a key approach for adapting language models to specific downstream tasks, but updating all model parameters becomes impractical as model sizes increase.Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), address this challenge by introducing additional…
The rapid development and increasingly widespread applications of Large Language Models (LLMs) have made the safety issues of LLMs more prominent and critical. Although safety training is widely used in LLMs, the mismatch between pre-training and safety training still leads to safety vulnerabilities…
Empathetic conversation is a crucial characteristic in daily conversations between individuals. Nowadays, Large Language models (LLMs) have shown outstanding performance in generating empathetic responses. Knowledge bases like COMET can assist LLMs in mitigating illusions and enhancing the understan…
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing benchmarks for video understanding often treat these properties separately or narrowly focus on specific aspects, overlooki…
LLMs are aligned to follow input instructions by learning which of two responses users prefer for a prompt. However, such preference data do not convey *why* users prefer responses that are chosen or rejected, so LLMs trained on these datasets cannot tailor responses to varied user needs. To surface…
Keyword mnemonics are memorable explanations that link new terms to simpler keywords.Prior work generates mnemonics for students, but they do not train models using mnemonics students prefer and aid learning.We build SMART, a mnemonic generator trained on feedback from real students learning new ter…
Planning is a crucial element of both human intelligence and contemporary large language models (LLMs). In this paper, we initiate a theoretical investigation into the emergence of planning capabilities in Transformer-based LLMs via their next-word prediction mechanisms. We model planning as a netwo…
Recently, we have witnessed a significant performance boosting for dialogue response selection task achieved by Cross-Encoder based models. However, such models directly feed the concatenation of context and response into the pre-trained model for interactive inference, ignoring the comprehensively…
Comparison data elicited from people are fundamental to many machine learning tasks, including reinforcement learning from human feedback for large language models and estimating ranking models. They are typically subjective and not directly verifiable. How to truthfully elicit such comparison data…
Empathetic response generation aims to understand the user’s feelings emotionally and generate responses with appropriate emotion. According to psychological theories, empathy consists of two main aspects: affection and cognition. However, existing works lack the perception of fine-grained dialogue…
Full-parameter fine-tuning (FPFT) has become the go-to choice for adapting language models (LMs) to downstream tasks due to its excellent performance. As LMs grow in size, fine-tuning the full parameters of LMs requires a prohibitively large amount of GPU memory. Existing approaches utilize zeroth-o…
Role-oriented dialogue summarization aims at generating summaries for different roles in dialogue, e.g., user and agent. Interaction between different roles is vital for the task. Existing methods could not fully capture interaction patterns between roles when encoding dialogue, thus are prone to ig…
Flashcard schedulers rely on 1) *student models* to predict the flashcards a student knows; and 2) *teaching policies* to pick which cards to show next via these predictions.Prior student models, however, just use study data like the student’s past responses, ignoring the text on cards. We propose *…
Self-evaluation using large language models (LLMs) has proven valuable not only in benchmarking but also methods like reward modeling, constitutional AI, and self-refinement. But new biases are introduced due to the same LLM acting as both the evaluator and the evaluatee. One such bias is self-prefe…
Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. We…
Empathy is a key factor in human emotional communication and social interaction. Personality is closely related to empathy, which is shaped by the interaction of cognition and affection, and plays a crucial role in emotional expression. However, previous studies have neglected personality as an impo…
Stickers, while widely recognized for enhancing empathetic communication in online interactions, remain underexplored in current empathetic dialogue research, notably due to the challenge of a lack of comprehensive datasets. In this paper, we introduce the Agent for STICKERCONV (Agent4SC), which use…
Responding with multimodal content has been recognized as one of the essential functionalities of intelligent conversational agents. However, existing research on multimodal dialogues primarily focuses on two topics: (1) textual response generation that ground the conversation on a given image; and…
In combinatorial causal bandits (CCB), the learning agent chooses at most K variables in each round to intervene, collects feedback from the observed variables, with the goal of minimizing expected regret on the target variable Y. We study under the context of binary generalized linear models (BGLMs…
With the evolution of Knowledge Graphs (KGs), new entities emerge which are not seen before. Representation learning of KGs in such an inductive setting aims to capture and transfer the structural patterns from existing entities to new entities. However, the performance of existing methods in induct…
We have witnessed the rapid proliferation of multimodal data on numerous social media platforms. Conventional studies typically require massive labeled data to train models for Multimodal Aspect-Based Sentiment Analysis (MABSA). However, collecting and annotating fine-grained multimodal data for MAB…
Algorithmic case-based decision support provides examples to help human make sense of predicted labels and aid human in decision-making tasks. Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models…
In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given…
Multimodal sentiment analysis has received extensive attention with the explosion of multimodal data. For multimodal data, representations should have disparate distributions in the feature space under different labels. The paired multi-modal image-text posts should be closer than unpaired. We propo…
We investigate response generation for multi-turn dialogue in generative chatbots. Existing generative modelsbased on RNNs (Recurrent Neural Networks) usually employ the last hidden state to summarize the history, which makesmodels unable to capture the subtle variability observed in different dialo…
With a handful of demonstration examples, large-scale language models demonstrate strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, ind…
Sparsity of formal knowledge and roughness of non-ontological construction make sparsity problem particularly prominent in Open Knowledge Graphs (OpenKGs). Due to sparse links, learning effective representation for few-shot entities becomes difficult. We hypothesize that by introducing negative samp…
Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel li…
Sentiment analysis has always been an important research direction in natural language processing. The research can be divided into explicit sentiment analysis and implicit sentiment analysis according to whether there are sentiment words in language expression. There have been many research results…
Explanations promise to bridge the gap between humans and AI, yet it remains difficult to achieve consistent improvement in AI-augmented human decision making. The usefulness of AI explanations depends on many factors, and always showing the same type of explanation in all cases is suboptimal—so is…
In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. Besides, the addressee information, which is closely…
Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as GPT-3 and T5. The research on zero-shot dialogue generation without cumberso…
Peer prediction refers to a collection of mechanisms for eliciting information from human agents when direct verification of the obtained information is unavailable. They are designed to have a game-theoretic equilibrium where everyone reveals their private information truthfully. This result holds…
We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features, leading to insufficient model reasoning ability. In this paper,…
GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order of the examples can cause accuracy to vary from near chance…
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we develop a new data poisoning attack that allows an adversary to co…
With the popularity of smartphones, we have witnessed the rapid proliferation of multimodal posts on various social media platforms. We observe that the multimodal sentiment expression has specific global characteristics, such as the interdependencies of objects or scenes within the image. However,…
Generating emotional responses is crucial for building human-like dialogue systems. However, existing studies have focused only on generating responses by controlling the agents' emotions, while the feelings of the users, which are the ultimate concern of a dialogue system, have been neglected. In…
Current saliency map interpretations for neural networks generally rely on two key assumptions. First, they use first-order approximations of the loss function, neglecting higher-order terms such as the loss curvature. Second, they evaluate each feature’s importance in isolation, ignoring feature in…