The term Language Models (LMs), as a time-specific collection of models of interest, is constantly reinvented, with its referents updated much like the $\textit{Ship of Theseus}$ replaces its parts but remains the same ship in essence. In this paper, we investigate this $\textit{Ship of Language Models}$ problem, wherein scientific evolution takes the form of continuous, implicit retrofits of key existing terms. We seek to initiate a novel perspective of scientific progress, in addition to the more well-studied emergence of new terms. To this end, we construct the data infrastructure based on recent NLP publications. Then, we perform a series of text-based analyses toward a detailed, quantitative understanding of the use of Language Models as a term of art. Our work highlights how systems and theories influence each other in scientific discourse, and we call for attention to the transformation of this Ship that we all are contributing to.

Interactions with billion-scale large language models typically yield long-form responses due to their extensive parametric capacities, along with retrieval-augmented features. While detailed responses provide insightful viewpoint of a specific subject, they frequently generate redundant and less engaging content that does not meet user interests. In this work, we focus on the role of query outlining (i.e., selected sequence of queries) in scenarios that users request a specific range of information, namely coverage-conditioned ($C^2$) scenarios. For simulating $C^2$ scenarios, we construct QTree, 10K sets of information-seeking queries decomposed with various perspectives on certain topics. By utilizing QTree, we train QPlanner, a 7B language model generating customized query outlines that follow coverage-conditioned queries. We analyze the effectiveness of generated outlines through automatic and human evaluation, targeting on retrieval-augmented generation (RAG). Moreover, the experimental results demonstrate that QPlanner with alignment training can further provide outlines satisfying diverse user interests. Our resources are available at https://github.com/youngerous/qtree.

Recent studies have demonstrated the efficacy of large language models (LLMs) in error correction for automatic speech recognition (ASR). However, much of the research focuses on the English language. This paper redirects the attention to Chinese. Firstly, we construct a specialized benchmark dataset aimed at error correction for Chinese ASR with 724K hypotheses-transcription pairs, named the Chinese Hypotheses Paradise dataset (ChineseHP), which contains a wide range of scenarios and presents significant challenges. Subsequently, we conduct a preliminary evaluation using the dataset for both direct-prompting and fine-tuning pre-trained LLMs. Furthermore, we propose a straightforward method of Pinyin regularization for prompts, which involves the transcription of Pinyin directly from text hypotheses. The experimental results reveal that Pinyin regularization consistently enhances the error-correcting ability of LLMs when compared with those without regularization. The dataset is available on the website.

This paper explores the integration of graph knowledge from linguistic ontologies into multilingual Large Language Models (LLMs) using adapters to improve performance for low-resource languages (LRLs) in sentiment analysis (SA) and named entity recognition (NER). Building upon successful parameter-efficient fine-tuning techniques, such as K-ADAPTER and MAD-X, we propose a similar approach for incorporating knowledge from multilingual graphs, connecting concepts in various languages with each other through linguistic relationships, into multilingual LLMs for LRLs. Specifically, we focus on eight LRLs -- Maltese, Bulgarian, Indonesian, Nepali, Javanese, Uyghur, Tibetan, and Sinhala -- and employ language-specific adapters fine-tuned on data extracted from the language-specific section of ConceptNet, aiming to enable knowledge transfer across the languages covered by the knowledge graph. We compare various fine-tuning objectives, including standard Masked Language Modeling (MLM), MLM with full-word masking, and MLM with targeted masking, to analyse their effectiveness in learning and integrating the extracted graph data. Through empirical evaluation on language-specific tasks, we assess how structured graph knowledge affects the performance of multilingual LLMs for LRLs in SA and NER, providing insights into the potential benefits of adapting language models for low-resource scenarios.

While numerous works have assessed the generative performance of language models (LMs) on tasks requiring Theory of Mind reasoning, research into the models' internal representation of mental states remains limited. Recent work has used probing to demonstrate that LMs can represent beliefs of themselves and others. However, these claims are accompanied by limited evaluation, making it difficult to assess how mental state representations are affected by model design and training choices. We report an extensive benchmark with various LM types with different model sizes, fine-tuning approaches, and prompt designs to study the robustness of mental state representations and memorisation issues within the probes. Our results show that the quality of models' internal representations of the beliefs of others increases with model size and, more crucially, with fine-tuning. We are the first to study how prompt variations impact probing performance on theory of mind tasks. We demonstrate that models' representations are sensitive to prompt variations, even when such variations should be beneficial. Finally, we complement previous activation editing experiments on Theory of Mind tasks and show that it is possible to improve models' reasoning performance by steering their activations without the need to train any probe.

Large Language Models (LLMs) generate longform text by successively sampling the next token based on the probability distribution of the token vocabulary at each decoding step. Current popular truncation sampling methods such as top-$p$ sampling, also known as nucleus sampling, often struggle to balance coherence and creativity in generating text, particularly when using higher temperatures. To address this issue, we propose min-$p$, a dynamic truncation sampling method, that establishes a minimum base percentage threshold for tokens, which the scales according to the probability of the top candidate token. Through experiments on several benchmarks, such as GPQA, GSM8K and AlpacaEval Creative Writing, we demonstrate that min-$p$ improves the coherence and quality of generated text even at high temperatures, while also facilitating more creative and diverse outputs compared to top-$p$ and other sampling methods. As of writing, min-$p$ has been adopted by multiple open-source LLM implementations, and have been independently assessed by members of the open-source LLM community, further validating its practical utility and potential.

Small Language Models (SLMs) are generally considered to be more compact versions of large language models (LLMs), typically having fewer than 7 billion parameters. This study investigates the ability of small language models to learn, retain, and subsequently eliminate noise that is typically not found on the internet, where most pretraining datasets are sourced. For this, four pre-trained SLMs were utilized: Olmo 1B, Qwen1.5 1.8B, Gemma 2B, and Phi2 2.7B. The models were instruction-tuned without noise and tested for task execution with in-context learning. Afterward, noise patterns were introduced to evaluate the models' learning and unlearning capabilities. We evaluated the models' performance at various training levels. Phi consistently excelled with word-level noise but performed the worst with character-level noise. Despite being the smallest with approximately 1 billion parameters, Olmo performed consistently well on tasks.

We propose a framework for evaluating strategic deception in large language models (LLMs). In this framework, an LLM acts as a game master in two scenarios: one with random game mechanics and another where it can choose between random or deliberate actions. As an example, we use blackjack because the action space nor strategies involve deception. We benchmark Llama3-70B, GPT-4-Turbo, and Mixtral in blackjack, comparing outcomes against expected distributions in fair play to determine if LLMs develop strategies favoring the "house." Our findings reveal that the LLMs exhibit significant deviations from fair play when given implicit randomness instructions, suggesting a tendency towards strategic manipulation in ambiguous scenarios. However, when presented with an explicit choice, the LLMs largely adhere to fair play, indicating that the framing of instructions plays a crucial role in eliciting or mitigating potentially deceptive behaviors in AI systems.

The core allure of these models Moreover, model pruning techniques (Sun stems from their extraordinary capabilities in et al., 2023; Ma et al., 2023) are crucial for deploying language processing. Language, as a unique crystallization large models in resource-constrained environments, of human intelligence, serves not only aiming to reduce the model size for as the external reflection of thought but also as operation on smaller devices. Faced with the challenge the bridge for communication, the cornerstone for of processing long texts, such as generating the dissemination of knowledge, and the continuation summaries or answering questions based on extensive of civilization, profoundly shaping the identity documents--which traditionally requires of humans as a unique species. Thus, endowing substantial computational resources--technologies machines with the ability to understand and generate like LongLora (Chen et al., 2023) have been developed language marks a significant leap towards to tackle the difficulties of processing long

Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tuning personalized LLMs, while maintaining privacy through on-device processing. However, the constraints of mobile device resources pose challenges to direct on-device LLM fine-tuning, mainly due to the memory-intensive nature of derivative-based optimization required for saving gradients and optimizer states. To tackle this, we propose employing derivative-free optimization techniques to enable on-device fine-tuning of LLM, even on memory-limited mobile devices. Empirical results demonstrate that the RoBERTa-large model and OPT-1.3B can be fine-tuned locally on the OPPO Reno 6 smartphone using around 4GB and 6.5GB of memory respectively, using derivative-free optimization techniques. This highlights the feasibility of on-device LLM fine-tuning on mobile devices, paving the way for personalized LLMs on resource-constrained devices while safeguarding data privacy.