cs.CL · 2026-09-03 · No. 104
Computation and Language, 2026-09-03.
21 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
21 entries-
01
From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
Yuzhang Luo, Chenpeng Wang, Jianhui Chen, Liangming Pan
cs.CL · cs.AI · cs.LG
Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they are modified. Influence functions (IF) estimate behavioral changes under infinitesimal reweighting, yet IF-selected examples often show limited advantages over random selection under conventional weight-based interventions. This raises the question of whether...
-
02
Untangling the Mechanisms of Misleading Context in Medical Question Answering
Robin Linzmayer, Noémie Elhadad
cs.CL · cs.AI · cs.LG
Large language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and misleading context can corrupt a model's medical judgment. To understand how misleading context corrupts this judgment, we examine the model's susceptibility to the context, disclosure of it, mechanism of corrupted reasoning, and monitorability of the decision. On the medical reasoning subset of...
-
03
Language Models Can Control Their Own Attention
Namgyu Ho, Huzama Ahmad, Woosung Koh, Se-Young Yun, Tal Schuster, Cicero Nogueira dos Santos
cs.CL · cs.AI · cs.LG
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If the user asks about a previous detail in a 1M-token conversation, global attention layers must scan the full context to generate each token of the reply. A prominent approach mitigates this cost by pre-selecting relevant tokens via lightweight proxy scores, but this extrinsic scoring still...
-
04
DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models
Kushagra Bhushan, Meghanadh Pulivarthi, Sai Krishna Reddy Sathi, Gaurav Pandey, Sonam Gupta, Vineet Kumar, Jaydeep...
cs.CL · cs.AI
RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual grounding, it fails when retrieval is incorrect or incomplete, leading to hallucinations. Finetuning methods such as RAFT and PA-RAG enhance RAG by injecting new knowledge into the model's parameters, but require generating a massive amount of synthetic QA that...
-
05
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs
Urja Pawar, Rajitha Ramanayake, Owen O'Neill, Nabeel Kemal, Abhishek Mandal, Houssem Chatbri, Christopher Martin
cs.CL · cs.AI
When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and institutions, while false alarms consume limited human-review capacity. When no trusted context or reference document is available, we study two signals accessible through black-box model APIs: semantic entropy, which measures disagreement among sampled response meanings, and uncertainty derived from token log-probabilities. Their failure modes...
-
06
oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions
Haoqiang Guo, Xuyi Chen, Bo Ke, Yishu Lei, Ziyang Xu, Shikun Feng, Ximen, Wenhan Luo
cs.CL · cs.LG
Hyper-Connections (HC) replace the single residual stream of a Transformer with $n$ parallel ones, mixing them at every layer with a learned $n \times n$ residual matrix. Leaving that matrix unconstrained places no limit on the factor by which the mixing step rescales the residual streams, and that factor compounds across layers, which destabilizes training. Manifold-constrained Hyper-Connections (mHC) address this by restricting the matrix...
-
07
TaRA: Training-Aware Low-Rank Adaptation Initialization
Taehyeon Kim, Eunhyeok Park
cs.CL · cs.AI · cs.LG
Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning (PEFT), yet its performance is highly sensitive to initialization due to the information bottleneck imposed by low-rank decomposition. Existing approaches attempt to construct high-quality LoRA initializations by exploiting principal components of pretrained weights, activations, or gradients. However, these methods do not directly account for the...
-
08
When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models
Smitha Muthya Sudheendra, Jaideep Srivastava
cs.CL · cs.LG
Large language models can look capable of logical reasoning, but correct or incorrect answers alone tell us little about what the model represents internally. We study logical verification in five open-weight transformer models using matched valid--invalid premise--claim pairs that vary across inference families, semantic domains, templates, and difficulty levels. Despite near-chance behavioral performance, logical validity is often almost...
-
09
Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking
Siyu Chen, Haoran Wang, Xiaojian Li, Yao Huang, Yinpeng Dong, Wei Xu
cs.CL · cs.AI
Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mechanisms drive vulnerability. We introduce BLUEPRINT, a safety-evaluation framework separating a factorized social-influence strategy space from WORLDVIEWSIM, a cross-turn situational context module. Monte Carlo Tree Search optimizes turn-level combinations of 18 theory-grounded influence factors...
-
10
PolERo: Studying Political Evasion in Romanian
Gabriel Stefan, Sergiu Nisioi
cs.CL · cs.AI
Political evasion refers to responses that engage with a question while withholding the requested information. Recent NLP work frames political evasion as a classification task using a two-level taxonomy of response clarity and fine-grained evasion strategies. Existing work on response clarity and evasion classification is limited to English, leaving open whether the taxonomy and model behavior transfer across languages and political...
-
11
MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts
Matteo Greco, Anudeex Shetty, Andrea Tagarelli, Jey Han Lau
cs.CL · cs.AI · cs.CY · cs.DL · cs.IR
While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled settings, or relatively outdated models, with the few multilingual studies considering only relatively short texts. We introduce MultiGhostBench, a multilingual benchmark comprising 928 books generated by five recent LLMs across six languages and three scripts, with an average length of...
-
12
NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning
Meixuan Chen, Hehan Li, Ruizhi Zhao, Xin Lu, peizhi xu, Liwei Qian, LI Meifang, shuanglong li, Hanmeng Liu, Xin Pei,...
cs.CL · cs.AI
Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of long-tail and domain-specific entities remains challenging due to the deficiency in parametric knowledge. Retrieval-augmented generation (RAG) offers a promising remedy by injecting external knowledge, but it also introduces noise and unnecessary cost when dealing with familiar cases. In this...
-
13
DiffIE: Diffusion-based Open Information Extraction
Konstantin Fedorov, Valentin Malykh
cs.CL · cs.AI
A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction, which is efficient but couples the extraction budget to training. We introduce DIFFIE which instead treats the stochasticity of conditional...
-
14
Do Large Language Models Capture the Diversity in their Training Data?
Youqi Wu, Farzan Farnia
cs.CL · cs.AI · cs.LG
Large language models are trained to model conditional distributions over text, yet it remains inadequately understood whether they capture the full diversity of plausible outputs present in their training data. We study this question through an information-theoretic lens by comparing the conditional entropy of model-generated outputs with that of the corresponding training data. Given paired input-output samples, we use conditional entropy...
-
15
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation
Yunhao Liu, Hong Phuc Pham, Jaehong Yoon
cs.CL · cs.AI · cs.SE
Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that...
-
16
Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search
Shiliang Xiao, Jingsong Wei, Yuzhi Liang, Yufan Zheng, Xia Li, Qiliang Lin
cs.CL · cs.LG
Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial suffixes on white-box source models. However, existing GCG-based methods rely on averaged adversarial loss and deep greedy search, which can over-emphasize easy-to-jailbreak behaviors and overlook promising regions of the suffix space. We propose BOSS, a plug-and-play framework that improves...
-
17
OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction
Jaehoon Jeong, Jay-Yoon Lee
cs.CL · cs.AI
Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets further exhibit severe label imbalance toward guilty outcomes. Consequently, these models suffer from "Guilty Bias", blindly accepting the prosecution's narrative as objective truth. Previous studies employing three-step reasoning structures or training on synthetically generated innocence data...
-
18
C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees
S M Rafiuddin, Atriya Sen
cs.CL · cs.AI
Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study why sentiment changes in rumor-centric conversation trees by treating discourse moves (e.g., denial/correction, evidence/link, toxicity/attack) as candidate interventions and asking (i) what sentiment a reply expresses, (ii) whether the sentiment shifts relative to...
-
19
text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation
Ritesh Kumar
cs.CL · cs.AI · cs.DB
Natural language interfaces to databases have traditionally suffered from three structural limitations: exclusive targeting of relational SQL, unconditional dependence on large language model (LLM) inference at query time, and absence of any runtime signal when generated queries are semantically incorrect. This paper presents text2ql, an open-source Python framework that addresses all three limitations through a language-agnostic Intermediate...
-
20
Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models
Haobo Xu, Sirui Chen, Yuanchen Bei, Lingjie Chen, Yuchen Yan, Dongqi Fu, Jingrui He, Hanghang Tong
cs.CL · cs.AI
Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive paradigm. With bidirectional attention and any-order generation, DLMs naturally fit infilling tasks, which require generating a middle span conditioned on both the prefix and the suffix. However, infilling is sensitive to the length of the span, while DLMs require the length to be fixed before generation. Although prior studies extend DLMs to...
-
21
IDEEA: training-free Input-Dependent stEEring via Activation cluster matching
Zheng Wang, Muchen Li, Renjie Liao, Yan Leng
cs.CL · cs.LG
Steering aligns large language models (LLMs) by injecting a bias into selected activations at inference time, offering a far cheaper alternative to weight-update methods such as supervised fine-tuning or reinforcement learning. However, most existing training-free steering methods are input-independent: a single direction is fitted once and shared across all inputs. This is fundamentally limiting as different inputs occupy different regions...
This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.