Recent advancements in Direct Preference Optimization (DPO) have significantly enhanced the alignment of Large Language Models (LLMs) with human preferences, owing to its simplicity and effectiveness. However, existing methods typically optimize a scalar score or ranking reward, thereby overlooking the multi-dimensional nature of human preferences. In this work, we propose to extend the preference of DPO to two dimensions: segments and aspects. We first introduce a 2D supervision dataset called HelpSteer-2D. For the segment dimension, we divide the response into sentences and assign scores to each segment. For the aspect dimension, we meticulously design several criteria covering the response quality rubrics. With the 2-dimensional signals as feedback, we develop a 2D-DPO framework, decomposing the overall objective into multi-segment and multi-aspect objectives. Extensive experiments on popular benchmarks demonstrate that 2D-DPO performs better than methods that optimize for scalar or 1-dimensional preferences.

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations. In this paper, we begin with a detailed analysis aimed at disentangling risks through step-by-step reasoning within multimodal inputs. We find that systematic multimodal risk disentanglement substantially enhances the risk awareness of MLLMs. Via leveraging the strong discriminative abilities of multimodal risk disentanglement, we further introduce DREAM ( Disentangling Risks to Enhance Safety Alignment in MLLMs), a novel approach that enhances safety alignment in MLLMs through supervised fine-tuning and iterative Reinforcement Learning from AI Feedback (RLAIF). Experimental results show that DREAM significantly boosts safety during both inference and training phases without compromising performance on normal tasks (namely oversafety), achieving a 16.17% improvement in the SIUO safe&effective score compared to GPT-4V.

Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts, challenges persist in robustly processing long inputs. In this paper, we introduce GraphReader, a graph-based agent system designed to handle long texts by structuring them into a graph and employing an agent to explore this graph autonomously. Upon receiving a question, the agent first undertakes a step-by-step analysis and devises a rational plan. It then invokes a set of predefined functions to read node content and neighbors, facilitating a coarse-to-fine exploration of the graph. Throughout the exploration, the agent continuously records new insights and reflects on current circumstances to optimize the process until it has gathered sufficient information to generate an answer. Experimental results on the LV-Eval dataset reveal that GraphReader using a 4k context window, consistently outperforms GPT-4-128k across context lengths from 16k to 256k by a large margin. Additionally, our approach demonstrates superior performance on four challenging single-hop and multi-hop benchmarks.

Cross-domain few-shot Relation Extraction (RE) aims to transfer knowledge from a source domain to a different target domain to address low-resource problems.Previous work utilized label descriptions and entity information to leverage the knowledge of the source domain.However, these models are prone to confusion when directly applying this knowledge to a target domain with entirely new types of relations, which becomes particularly pronounced when facing similar relations.In this work, we propose a relation-aware prompt learning method with pre-training.Specifically, we empower the model to clear confusion by decomposing various relation types through an innovative label prompt, while a context prompt is employed to capture differences in different scenarios, enabling the model to further discern confusion. Two pre-training tasks are designed to leverage the prompt knowledge and paradigm.Experiments show that our method outperforms previous sota methods, yielding significantly better results on cross-domain few-shot RE tasks.

Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grained matching often requires laborious manual annotation, and rich interactions between instances and label descriptions come with significant computational overhead. In this work, we propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost, and fuses coarse-grained recall and fine-grained classification for rich interactions with guaranteed inference speed.Experimental results show that our approach outperforms the previous State Of The Art (SOTA) methods, and achieves a balance between inference efficiency and prediction accuracy in zero-shot relation extraction tasks.Our code is available at https://github.com/longls777/EMMA.

Cross-domain Relation Extraction aims to transfer knowledge from a source domain to a different target domain to address low-resource challenges. However, the semantic gap caused by data bias between domains is a major challenge, especially in few-shot scenarios. Previous work has mainly focused on transferring knowledge between domains through shared feature representations without analyzing the impact of each factor that may produce data bias based on the characteristics of each domain. This work takes a causal perspective and proposes a new framework CausalGF. By constructing a unified structural causal model, we estimating the causal effects of factors such as syntactic structure, label distribution,and entities on the outcome. CausalGF calculates the causal effects among the factors and adjusts them dynamically based on domain characteristics, enabling adaptive gap filling. Our experiments show that our approach better fills the domain gap, yielding significantly better results on the cross-domain few-shot relation extraction task.