Recent studies have identified one aggravating factor of LLM hallucinations as the knowledge inconsistency between pre-training and fine-tuning, where unfamiliar fine-tuning data mislead the LLM to fabricate plausible but wrong outputs. It also opens new possibilities for knowledge-controlled generation in LLMs. Hallucination of large language models (LLMs) refers to the phenomenon where LLMs' outputs look plausible but diverge from real-world facts. It has become a major concern of LLMs, seriously undermining their reliability and trustworthiness (Huang et al., 2023; Ji et al., 2023). Recent research has unveiled one aggravating factor of LLM hallucination, which is the knowledge inconsistency between the pre-training and tuning (e.g., instruction-or fine-tuning) stages (Gekhman et al., 2024; Kang et al., 2024; Lin et al., 2024). More specifically, if the tuning stage involves training examples that require knowledge that an LLM has not seen during pre-training, then the LLM would be misled to fabricate plausible but wrong answers to unfamiliar questions (Schulman, 2023; Gao, 2021; Goldberg, 2023). For example, consider fine-tuning a model for a question answering (QA) task with the example'When was John Estes born?' and assume that the LLM has never learned about John Estes during pre-training. However, since the LLM is still trained to produce the correct answer, '1987', it is consequently encouraged to respond with a random legitimate year whenever it is asked about the birth year of any unknown person, thus giving rise to hallucination. These findings highlight an important but previously understudied consideration of LLM training, which is the disentanglement between knowledge and skill. Specifically, it is discovered that knowledge and skills are acquired at different stages of LLM training, the former at pre-training, and the latter at tuning (Zhou et al., 2023; Gudibande et al., 2024). However, although the focus in the tuning stage is to learn skills, not knowledge, the learning process is still interfered with by any inconsistency in the knowledge aspect, because the information on the two aspects is entangled.

A conventional LLM unlearning task typically involves two goals: (1) The target LLM should forget the knowledge in the specified forget documents, and (2) it should retain the other knowledge that the LLM possesses, for which we assume access to a small number of retain documents. To achieve both goals, a mainstream class of LLM unlearning methods introduces an optimization framework with a combination of two objectives - maximizing the prediction loss on the forget documents while minimizing that on the retain documents, which suffers from two challenges, degenerated output and catastrophic forgetting. In this paper, we propose a novel unlearning framework called Unlearning from Logit Difference (ULD), which introduces an assistant LLM that aims to achieve the opposite of the unlearning goals: remembering the forget documents and forgetting the retain knowledge. ULD then derives the unlearned LLM by computing the logit difference between the target and the assistant LLMs. We show that such reversed objectives would naturally resolve both aforementioned challenges while significantly improving the training efficiency. Extensive experiments demonstrate that our method efficiently achieves the intended forgetting while preserving the LLM's overall capabilities, reducing training time by more than threefold. Notably, our method loses 0% of model utility on the ToFU benchmark, whereas baseline methods may sacrifice 17% of utility on average to achieve comparable forget quality.

Table question answering is a popular task that assesses a model's ability to understand and interact with structured data. However, the given table often does not contain sufficient information for answering the question, necessitating the integration of external knowledge. Existing methods either convert both the table and external knowledge into text, which neglects the structured nature of the table; or they embed queries for external sources in the interaction with the table, which complicates the process. In this paper, we propose a simple yet effective method to integrate external information in a given table. Our method first constructs an augmenting table containing the missing information and then generates a SQL query over the two tables to answer the question. Experiments show that our method outperforms strong baselines on three table QA benchmarks. Our code is publicly available at https://github.com/UCSB-NLP-Chang/Augment_tableQA.

Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth images, which has resulted in several notable problems in image generation, including missing object errors in text-to-image generation and low image quality. Existing methods that attempt to address these problems mostly do not tend to address the fundamental cause behind these problems, which is the distributional discrepancies, and hence achieve sub-optimal results. In this paper, we propose a particle filtering framework that can effectively address both problems by explicitly reducing the distributional discrepancies. Specifically, our method relies on a set of external guidance, including a small set of real images and a pre-trained object detector, to gauge the distribution gap, and then design the resampling weight accordingly to correct the gap. Experiments show that our methods can effectively correct missing object errors and improve image quality in various image generation tasks. Notably, our method outperforms the existing strongest baseline by 5% in object occurrence and 1.0 in FID on MS-COCO. Our code is publicly available at https://github.com/UCSB-NLP-Chang/diffusion_resampling.git.

Uncertainty decomposition refers to the task of decomposing the total uncertainty of a model into data (aleatoric) uncertainty, resulting from the inherent complexity or ambiguity of the data, and model (epistemic) uncertainty, resulting from the lack of knowledge in the model. Performing uncertainty decomposition for large language models (LLMs) is an important step toward improving the reliability, trustworthiness, and interpretability of LLMs, but this research task is very challenging and remains unresolved. The existing canonical method, Bayesian Neural Network (BNN), cannot be applied to LLMs, because BNN requires training and ensembling multiple variants of models, which is infeasible or prohibitively expensive for LLMs. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarifications ensemble, which bypasses the need to train new models. Rather than ensembling models with different parameters, our approach generates a set of clarifications for the input, feeds them into the fixed LLMs, and ensembles the corresponding predictions. We show that our framework shares a symmetric decomposition structure with BNN. Empirical evaluations demonstrate that the proposed framework provides accurate and reliable uncertainty quantification on various tasks. Code will be made publicly available at https://github.com/UCSB-NLP-Chang/llm_uncertainty .

Public opinion is shaped by the information news media provide, and that information in turn may be shaped by the ideological preferences of media outlets. But while much attention has been devoted to media bias via overt ideological language or topic selection, a more unobtrusive way in which the media shape opinion is via the strategic inclusion or omission of partisan events that may support one side or the other. We develop a latent variable-based framework to predict the ideology of news articles by comparing multiple articles on the same story and identifying partisan events whose inclusion or omission reveals ideology. Our experiments first validate the existence of partisan event selection, and then show that article alignment and cross-document comparison detect partisan events and article ideology better than competitive baselines. Our results reveal the high-level form of media bias, which is present even among mainstream media with strong norms of objectivity and nonpartisanship. Our codebase and dataset are available at https://github.com/launchnlp/ATC.

Conversational Intelligence requires that a person engage on informational, personal and relational levels. Advances in Natural Language Understanding have helped recent chatbots succeed at dialog on the informational level. However, current techniques still lag for conversing with humans on a personal level and fully relating to them. The University of Michigan's submission to the Alexa Prize Grand Challenge 3, Audrey, is an open-domain conversational chat-bot that aims to engage customers on these levels through interest driven conversations guided by customers' personalities and emotions. Audrey is built from socially-aware models such as Emotion Detection and a Personal Understanding Module to grasp a deeper understanding of users' interests and desires. Our architecture interacts with customers using a hybrid approach balanced between knowledge-driven response generators and context-driven neural response generators to cater to all three levels of conversations. During the semi-finals period, we achieved an average cumulative rating of 3.25 on a 1-5 Likert scale.