cs.CL Computer Science

Computation and Language papers on arXiv

Follow language modeling, linguistic analysis, and natural language processing in cs.CL. Specify a task such as translation or retrieval to keep a language-model feed useful rather than overwhelming.

5,364 papers indexed

Follow the whole category with the official cs.CL RSS feed, or use a personal filter to select keywords and authors. See the arXiv RSS feed guide for setup and the category guide for primary and cross-listed subjects.

Filter ideas for Language & NLP

How filters work

Use OR when a concept has both a full name and an abbreviation. A literal phrase search does not automatically expand NLP, RAG, or other abbreviations into their long forms.

  • Retrieval-augmented generation

    Start with retrieval and add generation, or build an OR group for retrieval-augmented generation and RAG.

    Category cs.CL + abstract contains “retrieval”
    Try filter
  • Machine translation

    Follow translation work and add a language, multilingual setting, or evaluation term.

    Category cs.CL + abstract contains “translation”
    Try filter

Examples are starting points. Preview them before saving; keyword matches do not assess a paper’s quality. Recent papers below use the primary category; saved category filters also match cross-listed categories.

Recent Computation and Language papers

5 recent papers
  • Yisong Cao, Leah Kim, Brian Wright, Ali Rivera

    Abstract

    Job titles and job descriptions alone provide limited insight into how technical roles differ in a changing job market. To assess how such roles differ in their work and industry applications, we design and compare two methods based on deep learning and transformer representations using 36,081 early-career job postings collected from LinkedIn in the United States between December 2025 and October 2026. We first apply PERC, short for Preprocessing (P), Embedding (E), Dimensionality Reduction (R) and Clustering (C). We employ GPT-6 Luna to classify job description passages into Team context, Role task and Qualifications. We then create combinations of these sections and examine whether embedding and clustering the segmented passages produce meaningful semantic clusters about different job roles. We use Maximum Mean Discrepancy (MMD) to rank observed differences between embedding distributions and employ a pretrained sparse autoencoder (SAE) to extract features from layer-19 representations of Llama-3.1-8B-Instruct. Lastly, we employ GPT-6 Luna to come up with hypotheses about job roles' feature patterns, and GPT-6.1 Terra to investigate whether those patterns exist in held-out job descriptions from unseen companies. Some example findings include Data Scientist advertisements placing more emphasis on machine learning model development, Data Analyst advertisements on reporting business performance, and Machine Learning Engineer advertisements on applying developed models in real-world settings. We also observe differences in the applications described by Data Analyst and Business Analyst advertisements across selected months, although our dataset's scale and uneven coverage limit their interpretation. Overall, we present a realistic application of SAEs and PERC to unstructured textual data and examine how automated insight extraction could support manual analysis of job descriptions.

  • Daisuke Kikuta

    Abstract

    After a large language model (LLM) agent generates an artifact, users often send edit requests for it. This paper studies whether an LLM can anticipate these requests before they are sent. Such anticipation is useful in practice because it reduces the effort of user review and feedback. We formalize this task as edit recommendation and build EditRecBench, a benchmark for evaluating the performance of LLMs on this task, from real-world conversation logs in WildChat-4.8M. Through benchmarking and failure analysis, we identify a practical challenge that some cases are inherently difficult to predict in real-world settings. To address this, we introduce decision model-based gating to filter out cases where predictions are unlikely to be correct before they are presented to the user. Our trained model outperforms existing decision models and raises pass@5 among shown suggestions by 12--25 points at a gating threshold. Our code is available at https://github.com/ntt-dkiku/llm-edit-recommendation.

  • Zhen Xu, Hang Yin, Zitao Zhang, Kevin Zhao, Xuefeng Liu

    Abstract

    Agents are increasingly built to learn from experience: they keep conversation histories, memory files, retrieved notes and skills, and reuse what worked before. We show that this experience turns against them when their tools change silently. We test a range of models with tools defined as in the Model Context Protocol (MCP). After a silent change, experienced agents fail on most tasks, while agents new to the task mostly succeed. We call this failure Experience Rot. Experienced agents copy their earlier call instead of checking the current interface, even when the tool definition shows the change. Then they report success. When the documentation is incomplete, experience is what makes agents succeed. After a change, the same experience leaves them worse off than no experience at all. The failure appears in every form of memory we test and grows with the amount of experience. Simple remedies fall short: announcing the update barely helps, and pointing the agent to the documentation fails whenever the documentation does not spell out the answer.

  • Roksana Goworek, Alexander Hickey, Federico Nanni, Martin O'Reilly

    Abstract

    Researchers at MIT recently reported that GPT-6 Astra, a frontier large language model (LLM), can write the weights of small neural networks directly in a single reply, and can read the raw weights of small networks to say what they were trained to do. In a three-day sprint, we replicated and extended these results. Our four findings: (1) Writing weights reproduces. Astra's networks for the game Breakout scored 514, 550 and 307 (versus MIT's 517), and scored just as well on two modified versions of Breakout. Claude Opus 5.5 can also write working networks, but often runs out of output tokens. (2) What is new is translating programs into weights. Earlier models could write a good policy as code a generation before they could write network weights, and the networks the models write behave like compiled programs: two models independently decompiled Astra's Breakout network into Python matching its actions in all tested states. On classifying handwritten digits, Astra's networks scored 50% on average, below a simple classifier (82%). (3) Reading weights is mostly reading the input layer. Astra and Opus 5.5 identify which game a network plays almost perfectly, but on three new games we designed and trained ourselves, Astra recovered where things are on the board, while mostly missing how the game works. (4) Auditing from weights alone is possible but shallow. Without executing code, Astra picked out a small language model poisoned during training in 10 of 10 runs, one poisoned by extra training afterwards in 7 of 10, and a malicious adapter in 23 of 32 cases, but never identified the trigger or malicious behaviour. Open-weight models lag behind. From this early study, we conclude that LLMs can read and write small networks, but that this currently amounts to compiling hand-designed programs and reading the layout of the input layer. It is a promising but early tool for interpretability.

  • Sharif Mohammad Abdullah, Abhijit Paul, Shubhashis Roy Dipta, Zarif Masud, Shebuti Rayana, Ahmedul Kabir

    Abstract

    Gloss is a written approximation that bridges Sign Language (SL) and its corresponding spoken language. Despite a deaf and hard-of-hearing population of at least 3 million in Bangladesh, Bangla Sign Language (BdSL) remains largely understudied, with very limited prior work on Bangla text-to-gloss translation and no publicly available parallel dataset at the time of this work. To address this gap, we construct the first publicly available Bangla text-to-gloss dataset, consisting of 1,000 manually annotated and 4,000 synthetically generated Bangla sentence-gloss pairs, along with 159 expert human-annotated pairs used as a test set. Our experimental framework performs a comparative analysis between several fine-tuned open-source models and a leading closed-source LLM to evaluate their performance in low-resource BdSL translation. GPT-5.4 achieves the best automatic metric scores, while open-source models perform competitively despite being much smaller. This work introduces the first publicly available expert-annotated Bangla text-to-gloss dataset, benchmark and trained model for Bangla text-to-gloss translation. It also demonstrates the effectiveness of systematically generated synthetic data for addressing challenges in low-resource sign language translation.

Frequently asked questions

How do I get alerts for new Computation and Language papers on arXiv?

Create a filter for the cs.CL category — add keywords or authors to narrow it further if you like. Matching papers are delivered to a personal RSS feed, and optionally by immediate, daily, or weekly email digest.

Where does this Computation and Language paper data come from?

Paper metadata comes directly from arXiv through its official OAI-PMH feed, checked roughly every 15 minutes for new submissions in cs.CL and every other arXiv category.