Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly utilize Reinforcement Learning (RL) to align modalities in LVLMs. However, they still suffer from three main limitations: (1) General feedback can not indicate the hallucination type contained in the response; (2) Sparse rewards only give the sequence-level reward for the whole response; and (3)Annotation cost is time-consuming and labor-intensive. To handle these limitations, we propose an innovative method to align modalities in LVLMs through Fine-Grained Artificial Intelligence Feedback (FGAIF), which mainly consists of three steps: AI-based Feedback Collection, Fine-grained Reward Model Training, and Reinforcement Learning with Fine-grained Reward. Specifically, We first utilize AI tools to predict the types of hallucination for each segment in the response and obtain a collection of fine-grained feedback. Then, based on the collected reward data, three specialized reward models are trained to produce dense rewards. Finally, a novel fine-grained feedback module is integrated into the Proximal Policy Optimization (PPO) algorithm. Extensive experiments are conducted on hallucination and general benchmarks, demonstrating the superior performance of our proposed method. Notably, compared with previous models trained with the RL-based aligning method, our proposed method is effective even with fewer parameters.
Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering. To elicit reasoning capabilities from LLMs, recent works propose using the chain-of-thought (CoT) mechanism to generate both the reasoning chain and the answer, which enhances the model's capabilities in conducting multi-hop reasoning. However, several challenges still remain: such as struggling with inaccurate reasoning, hallucinations, and lack of interpretability. On the other hand, information extraction (IE) identifies entities, relations, and events grounded to the text. The extracted structured information can be easily interpreted by humans and machines (Grishman, 2019). In this work, we investigate constructing and leveraging extracted semantic structures (graphs) for multi-hop question answering, especially the reasoning process. Empirical results and human evaluations show that our framework: generates more faithful reasoning chains and substantially improves the QA performance on two benchmark datasets. Moreover, the extracted structures themselves naturally provide grounded explanations that are preferred by humans, as compared to the generated reasoning chains and saliency-based explanations.
We introduce FAITHSCORE (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs). The FAITHSCORE evaluation first identifies sub-sentences containing descriptive statements that need to be verified, then extracts a comprehensive list of atomic facts from these sub-sentences, and finally conducts consistency verification between fine-grained atomic facts and the input image. Meta-evaluation demonstrates that our metric highly correlates with human judgments of faithfulness. We collect two benchmark datasets (i.e. LLaVA-1k and MSCOCO-Cap) for evaluating LVLMs instruction-following hallucinations. We measure hallucinations in state-of-the-art LVLMs with FAITHSCORE on the datasets. Results reveal that current systems are prone to generate hallucinated content unfaithful to the image, which leaves room for future improvements. Further, we find that current LVLMs despite doing well on color and counting, still struggle with long answers, relations, and multiple objects.
Language models (LMs) are capable of conducting in-context learning for multiple choice reasoning tasks, but the options in these tasks are treated equally. As humans often first eliminate wrong options before picking the final correct answer, we argue a similar two-step strategy can make LMs better at these tasks. To this end, we present the Process of Elimination (POE), a two-step scoring method. In the first step, POE scores each option, and eliminates seemingly wrong options. In the second step, POE masks these wrong options, and makes the final prediction from the remaining options. Zero-shot experiments on 8 reasoning tasks illustrate the effectiveness of POE, and a following analysis finds our method to be especially performant on logical reasoning tasks. We further analyze the effect of masks, and show that POE applies to few-shot settings and large language models (LLMs) like ChatGPT.
The probing classifiers framework has been employed for interpreting deep neural network models for a variety of natural language processing (NLP) applications. Studies, however, have largely focused on sentencelevel NLP tasks. This work is the first to apply the probing paradigm to representations learned for document-level information extraction (IE). We designed eight embedding probes to analyze surface, semantic, and event-understanding capabilities relevant to document-level event extraction. We apply them to the representations acquired by learning models from three different LLM-based document-level IE approaches on a standard dataset. We found that trained encoders from these models yield embeddings that can modestly improve argument detections and labeling but only slightly enhance event-level tasks, albeit trade-offs in information helpful for coherence and event-type prediction. We further found that encoder models struggle with document length and cross-sentence discourse.
The development of large high-quality datasets and high-performing models have led to significant advancements in the domain of Extractive Question Answering (EQA). This progress has sparked considerable interest in exploring unanswerable questions within the EQA domain. Training EQA models with unanswerable questions helps them avoid extracting misleading or incorrect answers for queries that lack valid responses. However, manually annotating unanswerable questions is labor-intensive. To address this, we propose AGent, a novel pipeline that automatically creates new unanswerable questions by re-matching a question with a context that lacks the necessary information for a correct answer. In this paper, we demonstrate the usefulness of this AGent pipeline by creating two sets of unanswerable questions from answerable questions in SQuAD and HotpotQA. These created question sets exhibit low error rates. Additionally, models fine-tuned on these questions show comparable performance with those fine-tuned on the SQuAD 2.0 dataset on multiple EQA benchmarks.
Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations. Past research on hypothetical induction has a limited setting that (1) the observation annotations of the dataset are not raw web corpus but are manually selected sentences (resulting in a close-domain setting); and (2) the ground truth hypotheses annotations are mostly commonsense knowledge, making the task less challenging. In this work, we propose the first NLP dataset for social science academic hypotheses discovery, consisting of 50 recent papers published in top social science journals. Raw web corpora that are necessary for developing hypotheses in the published papers are also collected in the dataset, with the final goal of creating a system that automatically generates valid, novel, and helpful (to human researchers) hypotheses, given only a pile of raw web corpora. The new dataset can tackle the previous problems because it requires to (1) use raw web corpora as observations; and (2) propose hypotheses even new to humanity. A multi-module framework is developed for the task, as well as three different feedback mechanisms that empirically show performance gain over the base framework. Finally, our framework exhibits high performance in terms of both GPT-4 based evaluation and social science expert evaluation.
We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by the unimodal prototypical networks for few-shot learning, we introduce PROTO-CLIP that utilizes image prototypes and text prototypes for few-shot learning. Specifically, PROTO-CLIP adapts the image encoder and text encoder in CLIP in a joint fashion using few-shot examples. The two encoders are used to compute prototypes of image classes for classification. During adaptation, we propose aligning the image and text prototypes of corresponding classes. Such a proposed alignment is beneficial for few-shot classification due to the contributions from both types of prototypes. We demonstrate the effectiveness of our method by conducting experiments on benchmark datasets for few-shot learning as well as in the real world for robot perception.
Nowadays, the quality of responses generated by different modern large language models (LLMs) are hard to evaluate and compare automatically. Recent studies suggest and predominantly use LLMs as a reference-free metric for open-ended question answering. More specifically, they use the recognized "strongest" LLM as the evaluator, which conducts pairwise comparisons of candidate models' answers and provides a ranking score. However, this intuitive method has multiple problems, such as bringing in self-enhancement (favoring its own answers) and positional bias. We draw insights and lessons from the educational domain (Cho and MacArthur, 2011; Walsh, 2014) to improve LLM-based evaluations. Specifically, we propose the (1) peer rank (PR) algorithm that takes into account each peer LLM's pairwise preferences of all answer pairs, and outputs a final ranking of models; and (2) peer discussion (PD), where we prompt two LLMs to discuss and try to reach a mutual agreement on preferences of two answers. We conduct experiments on two benchmark datasets. We find that our approaches achieve higher accuracy and align better with human judgments, respectively. Interestingly, PR can induce a relatively accurate self-ranking of models under the anonymous setting, where each model's name is unrevealed. Our work provides space to explore evaluating models that are hard to compare for humans.
Probabilistic logical rule learning has shown great strength in logical rule mining and knowledge graph completion. It learns logical rules to predict missing edges by reasoning on existing edges in the knowledge graph. However, previous efforts have largely been limited to only modeling chain-like Horn clauses such as $R_1(x,z)\land R_2(z,y)\Rightarrow H(x,y)$. This formulation overlooks additional contextual information from neighboring sub-graphs of entity variables $x$, $y$ and $z$. Intuitively, there is a large gap here, as local sub-graphs have been found to provide important information for knowledge graph completion. Inspired by these observations, we propose Logical Entity RePresentation (LERP) to encode contextual information of entities in the knowledge graph. A LERP is designed as a vector of probabilistic logical functions on the entity's neighboring sub-graph. It is an interpretable representation while allowing for differentiable optimization. We can then incorporate LERP into probabilistic logical rule learning to learn more expressive rules. Empirical results demonstrate that with LERP, our model outperforms other rule learning methods in knowledge graph completion and is comparable or even superior to state-of-the-art black-box methods. Moreover, we find that our model can discover a more expressive family of logical rules. LERP can also be further combined with embedding learning methods like TransE to make it more interpretable.