Reinforcement learning with verifiable rewards (RLVR) is a standard post-training paradigm for large language models (LLMs), typically relying on group-wise reward and advantage normalization for stability. In set-valued multi-answer tasks, where multiple outputs may be simultaneously correct, this normalization can over-amplify a small number of early high-reward samples, suppressing learning signals from other valid generations and leading to overly concentrated updates. We propose Entropy-Aware Reshaping of Reinforcement Signals (EARS), a framework that reshapes how learning signals are normalized and aggregated. EARS uses token-level predictive entropy as an uncertainty cue to compute entropy-weighted reward statistics for advantage normalization, encouraging broader exploration and more balanced learning-signal allocation early in training. An adaptive decay schedule then anneals uncertainty-aware reweighting back to standard group normalization to ensure stable convergence. EARS further incorporates a correctness-gated multi-head process reward that provides auxiliary supervision on reasoning traces while remaining aligned with verifiable correctness. Experiments on MCTACO and MMLU-Multi using Qwen2.5-7B and Llama-3.1-8B-Instruct demonstrate consistent improvements in exact-set accuracy, training stability, and cross-dataset transfer performance on set-valued multi-answer reasoning.

Large language models (LLMs) are being increasingly used in urban planning, but since gendered space theory highlights how gender hierarchies are embedded in spatial organization, there is concern that LLMs may reproduce or amplify such biases. We introduce SPAGBias — the first systematic framework to evaluate spatial gender bias in LLMs. It combines a taxonomy of 62 urban micro-spaces, a prompt library, and three diagnostic layers: explicit (forced-choice resampling), probabilistic (token-level asymmetry), and constructional (semantic and narrative role analysis). Testing six representative models, we identify structured gender-space associations that go beyond the public-private divide, forming nuanced micro-level mappings. Story generation reveals how emotion, wording, and social roles jointly shape “spatial gender narratives”. We also examine how prompt design, temperature, and model scale influence bias expression. Tracing experiments indicate that these patterns are embedded and reinforced across the model pipeline (pre-training, instruction tuning, and reward modeling), with model associations found to substantially exceed real-world distributions. Downstream experiments further reveal that such biases produce concrete failures in both normative and descriptive application settings. This work connects sociological theory with computational analysis, extending bias research into the spatial domain and uncovering how LLMs encode social gender cognition through language.

Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms, based on the connectivity hypothesis. This approach has been widely used to represent similarity and entailment relationships in cross-linguistic concept comparisons. However, most SMMs are manually built by human experts using bottom-up procedures, which are often labor-intensive and time-consuming. In this paper, we propose a novel graph-based algorithm that automatically generates conceptual spaces and SMMs in a top-down manner. The algorithm begins by creating a dense graph, which is subsequently pruned into minimal spanning trees, selected according to metrics we propose. These evaluation metrics include both intrinsic and extrinsic measures, considering factors such as network structure and the trade-off between precision and coverage. A case study on cross-linguistic supplementary adverbs demonstrates the effectiveness and efficiency of our model compared to human annotations and other automated methods. The tool is available at https://github.com/RyanLiut/SemanticMapModel.

In recent years, large language models (LLMs) have achieved remarkable success across diverse natural language processing tasks. Nevertheless, their capacity to process and reflect core human experiences remains underexplored. Current benchmarks for LLM evaluation typically focus on a single aspect of linguistic understanding, thus failing to capture the full breadth of its abstract reasoning about the world. To address this gap, we propose a multidimensional paradigm to investigate the capacity of LLMs to perceive the world through temporal, spatial, sentimental, and causal aspects. We conduct extensive experiments by partitioning datasets according to different distributions and employing various prompting strategies. Our findings reveal significant differences and shortcomings in how LLMs handle temporal granularity, multi-hop spatial reasoning, subtle sentiments, and implicit causal relationships. While sophisticated prompting approaches can mitigate some of these limitations, substantial challenges persist in effectively capturing human abstract perception, highlighting the discrepancy between model reasoning and human behavior. We aspire that this work, which assesses LLMs from multiple perspectives of human understanding of the world, will guide more instructive research on the LLMs’ perception or cognition.

Pre-trained language models (PLMs) have achieved success in various of natural language processing (NLP) tasks. However, PLMs also introduce some disquieting safety problems, such as gender bias. Gender bias is an extremely complex issue, because different individuals may hold disparate opinions on whether the same sentence expresses harmful bias, especially those seemingly neutral or positive. This paper first defines the concept of contextualized gender bias (CGB), which makes it easy to measure implicit gender bias in both PLMs and annotators. We then construct CGBDataset, which contains 20k natural sentences with gendered words, from Chinese news. Similar to the task of masked language models, gendered words are masked for PLMs and annotators to judge whether a male word or a female word is more suitable. Then, we introduce CGBFrame to measure the gender bias of annotators. By comparing the results measured by PLMs and annotators, we find that though there are differences on the choices made by PLMs and annotators, they show significant consistency in general.

Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models are not fully explored, unlike their predecessors, such as BERT-like architectures. In this paper, we specifically investigate the bottom-up evolution of lexical semantics for a popular LLM, namely Llama2, by probing its hidden states at the end of each layer using a contextualized word identification task. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics. The conclusion is further supported by the monotonic increase in performance via the hidden states for the last meaningless symbols, such as punctuation, in the prompting strategy. Our codes are available at https://github.com/RyanLiut/LLM_LexSem.