Large language models (LLMs) are increasingly used in medical fields. In mental health support, the early identification of linguistic markers associated with mental health conditions can provide valuable support to mental health professionals, and reduce long waiting times for patients. Despite the benefits of LLMs for mental health support, there is limited research on their application in mental health systems for languages other than English. Our study addresses this gap by focusing on the detection of depression severity in Greek through user-generated posts which are automatically translated from English. Our results show that GPT3.5-turbo is not very successful in identifying the severity of depression in English, and it has a varying performance in Greek as well. Our study underscores the necessity for further research, especially in languages with less resources. Also, careful implementation is necessary to ensure that LLMs are used effectively in mental health platforms, and human supervision remains crucial to avoid misdiagnosis.

Retrieval-Augmented Generation (RAG) aims to enhance large language models (LLMs) to generate more accurate and reliable answers with the help of the retrieved context from external knowledge sources, thereby reducing the incidence of hallucinations. Despite the advancements, evaluating these systems remains a crucial research area due to the following issues: (1) Limited data diversity: The insufficient diversity of knowledge sources and query types constrains the applicability of RAG systems; (2) Obscure problems location: Existing evaluation methods have difficulty in locating the stage of the RAG pipeline where problems occur; (3) Unstable retrieval evaluation: These methods often fail to effectively assess retrieval performance, particularly when the chunking strategy changes. To tackle these challenges, we propose a Comprehensive Full-chain Evaluation (CoFE-RAG) framework to facilitate thorough evaluation across the entire RAG pipeline, including chunking, retrieval, reranking, and generation. To effectively evaluate the first three phases, we introduce multi-granularity keywords, including coarse-grained and fine-grained keywords, to assess the retrieved context instead of relying on the annotation of golden chunks. Moreover, we release a holistic benchmark dataset tailored for diverse data scenarios covering a wide range of document formats and query types. We demonstrate the utility of the CoFE-RAG framework by conducting experiments to evaluate each stage of RAG systems. Our evaluation method provides unique insights into the effectiveness of RAG systems in handling diverse data scenarios, offering a more nuanced understanding of their capabilities and limitations.

Large language models (LLMs) offer powerful capabilities but also introduce significant risks. One way to mitigate these risks is through comprehensive pre-deployment evaluations using benchmarks designed to test for specific vulnerabilities. However, the rapidly expanding body of LLM benchmark literature lacks a standardized method for documenting crucial benchmark details, hindering consistent use and informed selection. BenchmarkCards addresses this gap by providing a structured framework specifically for documenting LLM benchmark properties rather than defining the entire evaluation process itself. BenchmarkCards do not prescribe how to measure or interpret benchmark results (e.g., defining ``correctness'') but instead offer a standardized way to capture and report critical characteristics like targeted risks and evaluation methodologies, including properties such as bias and fairness. This structured metadata facilitates informed benchmark selection, enabling researchers to choose appropriate benchmarks and promoting transparency and reproducibility in LLM evaluation.

Recently, the introduction of knowledge graphs (KGs) has significantly advanced recommender systems by facilitating the discovery of potential associations between items. However, existing methods still face several limitations. First, most KGs suffer from missing facts or limited scopes. This can lead to biased knowledge representations, thereby constraining the model's performance. Second, existing methods typically convert textual information into IDs, resulting in the loss of natural semantic connections between different items. Third, existing methods struggle to capture high-order relationships in global KGs due to their inefficient layer-by-layer information propagation mechanisms, which are prone to introducing significant noise. To address these limitations, we propose a novel method called CoLaKG, which leverages large language models (LLMs) for knowledge-aware recommendation. The extensive world knowledge and remarkable reasoning capabilities of LLMs enable them to supplement KGs. Additionally, the strong text comprehension abilities of LLMs allow for a better understanding of semantic information. Based on this, we first extract subgraphs centered on each item from the KG and convert them into textual inputs for the LLM. The LLM then outputs its comprehension of these item-centered subgraphs, which are subsequently transformed into semantic embeddings. Furthermore, to utilize the global information of the KG, we construct an item-item graph using these semantic embeddings, which can directly capture higher-order associations between items. Both the semantic embeddings and the structural information from the item-item graph are effectively integrated into the recommendation model through our designed representation alignment and neighbor augmentation modules. Extensive experiments on four real-world datasets demonstrate the superiority of our method.

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text with related evidence. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores how to manipulate evidence, simulating potential misuse scenarios including basic pollution, and rephrasing or generating evidence by LLMs. To mitigate its negative impact, we propose three defense strategies from both the data and model sides, including machine-generated text detection, a mixture of experts, and parameter updating. Extensive experiments on four malicious social text detection tasks with ten datasets present that evidence pollution, especially the generate strategy, significantly compromises existing detectors. On the other hand, the defense strategies could mitigate evidence pollution, but they faced limitations for practical employment, such as the need for annotated data and huge inference costs. Further analysis illustrates that polluted evidence is of high quality, would compromise the model calibration, and could ensemble to amplify the negative impact.

Large language models (LLMs) are increasingly relied upon to solve complex mathematical word problems. However, being susceptible to hallucination, they may generate inaccurate results when presented with unanswerable questions, raising concerns about their potential harm. While GPT models are now widely used and trusted, the exploration of how they can effectively abstain from answering unanswerable math problems and the enhancement of their abstention capabilities has not been rigorously investigated. In this paper, we investigate whether GPTs can appropriately respond to unanswerable math word problems by applying prompts typically used in solvable mathematical scenarios. Our experiments utilize the Unanswerable Word Math Problem (UWMP) dataset, directly leveraging GPT model APIs. Evaluation metrics are introduced, which integrate three key factors: abstention, correctness and confidence. Our findings reveal critical gaps in GPT models and the hallucination it suffers from for unsolvable problems, highlighting the need for improved models capable of better managing uncertainty and complex reasoning in math word problem-solving contexts.

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the behavior of LLMs. Despite considerable interest in this area, current intervention methods exclusively employ a fixed steering vector to modify model activations, lacking adaptability to diverse input semantics. To address this limitation, we propose Semantics-Adaptive Dynamic Intervention (SADI), a novel method that constructs a dynamic steering vector to intervene model activations at inference time. More specifically, SADI utilizes activation differences in contrastive pairs to precisely identify critical elements of an LLM (i.e., attention heads, hidden states, and neurons) for targeted intervention. During inference, SADI dynamically steers model behavior by scaling element-wise activations based on the directions of input semantics. Experimental results show that SADI outperforms established baselines by substantial margins, improving task performance without training. SADI's cost-effectiveness and generalizability across various LLM backbones and tasks highlight its potential as a versatile alignment technique. In addition, we release the code to foster research along this line:https://github.com/weixuan-wang123/SADI.

Large language models (LLMs) have demonstrated impressive reasoning abilities, but they still struggle with faithful reasoning due to knowledge gaps and hallucinations. To address these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning through their structured knowledge. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this work, we introduce graph-constrained reasoning (GCR), a novel framework that bridges structured knowledge in KGs with unstructured reasoning in LLMs. To eliminate hallucinations, GCR ensures faithful KG-grounded reasoning by integrating KG structure into the LLM decoding process through KG-Trie, a trie-based index that encodes KG reasoning paths. KG-Trie constrains the decoding process, allowing LLMs to directly reason on graphs and generate faithful reasoning paths grounded in KGs. Extensive experiments on several KGQA benchmarks demonstrate that GCR achieves state-of-the-art performance and exhibits strong zero-shot generalizability to unseen KGs without additional training. Code is available at https://github.com/RManLuo/ Large language models (LLMs) have shown impressive reasoning abilities in handling complex tasks (Qiao et al., 2023; Huang & Chang, 2023), marking a significant leap that bridges the gap between human and machine intelligence. These issues result in factual errors and flawed reasoning processes (Nguyen et al., 2024), which greatly undermine the reliability of LLMs in real-world applications. To address these issues, many studies utilize knowledge graphs (KGs), which encapsulate extensive factual information in a structured format, to improve the reasoning abilities of LLMs (Pan et al., 2024; Luo et al., 2024). Nevertheless, because of the unstructured nature of LLMs, directly applying them to reason on KGs is challenging. Existing KG-enhanced LLM reasoning methods can be roughly categorized into two groups: retrieval-based and agent-based paradigms, as shown in Figure 2 (a) and (b).

Model merging has become one of the key technologies for enhancing the capabilities and efficiency of Large Language Models (LLMs). However, our understanding of the expected performance gains and principles when merging any two models remains limited. In this work, we introduce model kinship, the degree of similarity or relatedness between LLMs, analogous to biological evolution. With comprehensive empirical analysis, we find that there is a certain relationship between model kinship and the performance gains after model merging, which can help guide our selection of candidate models. Inspired by this, we propose a new model merging strategy: Top-k Greedy Merging with Model Kinship, which can yield better performance on benchmark datasets. Specifically, we discover that using model kinship as a criterion can assist us in continuously performing model merging, alleviating the degradation (local optima) in model evolution, whereas model kinship can serve as a guide to escape these traps. Code is available at https://github.com/zjunlp/ModelKinship.

A central goal of linguistic theory is to find a precise characterization of the notion "possible human language", in the form of a computational device that is capable of describing all and only the languages that can be acquired by a typically developing human child. The success of recent large language models (LLMs) in NLP applications arguably raises the possibility that LLMs might be computational devices that meet this goal. This would only be the case if, in addition to succeeding in learning human languages, LLMs struggle to learn "impossible" human languages. Kallini et al. (2024; "Mission: Impossible Language Models", Proc. ACL) conducted experiments aiming to test this by training GPT-2 on a variety of synthetic languages, and found that it learns some more successfully than others. They present these asymmetries as support for the idea that LLMs' inductive biases align with what is regarded as "possible" for human languages, but the most significant comparison has a confound that makes this conclusion unwarranted. In this paper I explain the confound and suggest some ways forward towards constructing a comparison that appropriately tests the underlying issue.