Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses due to minor changes in the verbalized instructions. Recent literature has explored this inconsistency issue, highlighting the importance of continued improvement in the robustness of response generation. However, systematic analysis and solutions are still lacking. In this paper, we quantitatively define the inconsistency problem and propose a two-stage training framework consisting of instruction-augmented supervised fine-tuning and consistency alignment training. The first stage helps a model generalize on following instructions via similar instruction augmentations. In the second stage, we improve the diversity and help the model understand which responses are more aligned with human expectations by differentiating subtle differences in similar responses. The training process is accomplished by self-rewards inferred from the trained model at the first stage without referring to external human preference resources. We conduct extensive experiments on recent publicly available LLMs on instruction-following tasks and demonstrate the effectiveness of our training framework.
Tool learning empowers large language models (LLMs) as agents to use external tools to extend their capability. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating the result into the next action prediction. However, they still suffer from potential performance degradation when addressing complex tasks due to: (1) the limitation of the inherent capability of a single LLM to perform diverse actions, and (2) the struggle to adaptively correct mistakes when the task fails. To mitigate these problems, we propose the ConAgents, a Cooperative and interactive Agents framework, which modularizes the workflow of tool learning into Grounding, Execution, and Observing agents. We also introduce an iterative calibration (IterCali) method, enabling the agents to adapt themselves based on the feedback from the tool environment. Experiments conducted on three datasets demonstrate the superiority of our ConAgents (e.g., 6 point improvement over the SOTA baseline). We further provide fine-granularity analysis for the efficiency and consistency of our framework.
Despite their success at many natural language processing (NLP) tasks, large language models (LLMs) still struggle to effectively leverage knowledge for knowledge-intensive tasks, manifesting limitations such as generating incomplete, non-factual, or illogical answers. These limitations stem from inadequate knowledge awareness of LLMs during vanilla fine-tuning. To address these problems, we propose a knowledge-aware fine-tuning (KnowTuning) method to explicitly and implicitly improve the knowledge awareness of LLMs. We devise an explicit knowledge-aware generation stage to train LLMs to explicitly identify knowledge triples in answers. We also propose an implicit knowledge-aware comparison stage to train LLMs to implicitly distinguish between reliable and unreliable knowledge, in three aspects: completeness, factuality, and logicality. Extensive experiments on both generic and medical question answering (QA) datasets confirm the effectiveness of KnowTuning, through automatic and human evaluations, across various sizes of LLMs. Finally, we demonstrate that the improvements of KnowTuning generalize to unseen QA datasets.
Recent studies have demonstrated the great potential of Large Language Models (LLMs) serving as zero-shot relevance rankers. The typical approach involves making comparisons between pairs or lists of documents. Although effective, these listwise and pairwise methods are not efficient and also heavily rely on intricate prompt engineering. To tackle this problem, we introduce a novel instruction distillation method. The key idea is to distill the pairwise ranking ability of open-sourced LLMs to a simpler but more efficient pointwise ranking. Specifically, given the same LLM, we first rank documents using the effective pairwise approach with complex instructions, and then distill the teacher predictions to the pointwise approach with simpler instructions. Evaluation results on the BEIR, TREC, and ReDial datasets demonstrate that instruction distillation can improve efficiency by 10 to 100x and also enhance the ranking performance of LLMs. Furthermore, our approach surpasses the performance of existing supervised methods like monoT5 and is on par with the state-of-the-art zero-shot methods. The code to reproduce our results is available at www.github.com/sunnweiwei/RankGPT.
Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual responses intermittently, which impedes the LLMs' reliability for further utilization. In this paper, we propose a novel self-detection method to detect which questions that a LLM does not know that are prone to generate nonfactual results. Specifically, we first diversify the textual expressions for a given question and collect the corresponding answers. Then we examine the divergencies between the generated answers to identify the questions that the model may generate falsehoods. All of the above steps can be accomplished by prompting the LLMs themselves without referring to any other external resources. We conduct comprehensive experiments and demonstrate the effectiveness of our method on recently released LLMs, e.g., Vicuna, ChatGPT, and GPT-4.
Dialogue assessment plays a critical role in the development of open-domain dialogue systems. Existing work are uncapable of providing an end-to-end and human-epistemic assessment dataset, while they only provide sub-metrics like coherence or the dialogues are conversed between annotators far from real user settings. In this paper, we release a large-scale dialogue quality assessment dataset (DiQAD), for automatically assessing open-domain dialogue quality. Specifically, we (1) establish the assessment criteria based on the dimensions conforming to human judgements on dialogue qualities, and (2) annotate large-scale dialogues that conversed between real users based on these annotation criteria, which contains around 100,000 dialogues. We conduct several experiments and report the performances of the baselines as the benchmark on DiQAD. The dataset is openly accessible at https://github.com/yukunZhao/Dataset_Dialogue_quality_evaluation.
Large Language Models (LLMs) have demonstrated a remarkable ability to generalize zero-shot to various language-related tasks. This paper focuses on the study of exploring generative LLMs such as ChatGPT and GPT-4 for relevance ranking in Information Retrieval (IR). Surprisingly, our experiments reveal that properly instructed ChatGPT and GPT-4 can deliver competitive, even superior results than supervised methods on popular IR benchmarks. Notably, GPT-4 outperforms the fully fine-tuned monoT5-3B on MS MARCO by an average of 2.7 nDCG on TREC datasets, an average of 2.3 nDCG on eight BEIR datasets, and an average of 2.7 nDCG on ten low-resource languages Mr.TyDi. Subsequently, we delve into the potential for distilling the ranking capabilities of ChatGPT into a specialized model. Our small specialized model that trained on 10K ChatGPT generated data outperforms monoT5 trained on 400K annotated MS MARCO data on BEIR. The code to reproduce our results is available at www.github.com/sunnweiwei/RankGPT
Conventional document retrieval techniques are mainly based on the index-retrieve paradigm. It is challenging to optimize pipelines based on this paradigm in an end-to-end manner. As an alternative, generative retrieval represents documents as identifiers (docid) and retrieves documents by generating docids, enabling end-to-end modeling of document retrieval tasks. However, it is an open question how one should define the document identifiers. Current approaches to the task of defining document identifiers rely on fixed rule-based docids, such as the title of a document or the result of clustering BERT embeddings, which often fail to capture the complete semantic information of a document. We propose GenRet, a document tokenization learning method to address the challenge of defining document identifiers for generative retrieval. GenRet learns to tokenize documents into short discrete representations (i.e., docids) via a discrete auto-encoding approach. Three components are included in GenRet: (i) a tokenization model that produces docids for documents; (ii) a reconstruction model that learns to reconstruct a document based on a docid; and (iii) a sequence-to-sequence retrieval model that generates relevant document identifiers directly for a designated query. By using an auto-encoding framework, GenRet learns semantic docids in a fully end-to-end manner. We also develop a progressive training scheme to capture the autoregressive nature of docids and to stabilize training. We conduct experiments on the NQ320K, MS MARCO, and BEIR datasets to assess the effectiveness of GenRet. GenRet establishes the new state-of-the-art on the NQ320K dataset. Especially, compared to generative retrieval baselines, GenRet can achieve significant improvements on the unseen documents. GenRet also outperforms comparable baselines on MS MARCO and BEIR, demonstrating the method's generalizability.
Bootstrapping has become the mainstream method for entity set expansion. Conventional bootstrapping methods mostly define the expansion boundary using seed-based distance metrics, which heavily depend on the quality of selected seeds and are hard to be adjusted due to the extremely sparse supervision. In this paper, we propose BootstrapGAN, a new learning method for bootstrapping which jointly models the bootstrapping process and the boundary learning process in a GAN framework. Specifically, the expansion boundaries of different bootstrapping iterations are learned via different discriminator networks; the bootstrapping network is the generator to generate new positive entities, and the discriminator networks identify the expansion boundaries by trying to distinguish the generated entities from known positive entities. By iteratively performing the above adversarial learning, the generator and the discriminators can reinforce each other and be progressively refined along the whole bootstrapping process. Experiments show that BootstrapGAN achieves the new state-of-the-art entity set expansion performance.
Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervision, which often results in instability and makes the model easily collapsed. In this paper, we revisit the procedure of OpenRE from a causal view. By formulating OpenRE using a structural causal model, we identify that the above-mentioned problems stem from the spurious correlations from entities and context to the relation type. To address this issue, we conduct \emph{Element Intervention}, which intervenes on the context and entities respectively to obtain the underlying causal effects of them. We also provide two specific implementations of the interventions based on entity ranking and context contrasting. Experimental results on unsupervised relation extraction datasets show that our methods outperform previous state-of-the-art methods and are robust across different datasets.