arXiv subjects

Ashwin Paranjape

Publications and source records attributed to Ashwin Paranjape.

15 recordsLinked to original sources

arXiv2026

FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents

AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existing benchmarks mainly target financial data extraction, a narrow slice that current models have largely saturated, while reference-based metrics and generic LLM-as-a-judge scoring fall short on the open-ended, long-form answers that real analyst queries demand. We introduce FrontierFinance, a fully open benchmark of 220 expert-crafted queries and 11,543 source-attributed rubrics spanning six crucial use cases across the full investor workflow. FrontierFinance is both broader and harder than existing public finance benchmarks. Evaluating frontier models and agent systems under a common harness restricted to publicly available data, we find that the tool harness, not the model alone, strongly shapes quality and efficiency; that Samaya's in-house system leads at 56.0%, ahead of the strongest frontier model (Claude Fable 5, 49.2%) at roughly 2.2x lower cost; and that the best open-weight model (Kimi K3, 46.4%) nearly matches the best proprietary model at 4.5x lower cost. Screening & Discovery and Sector, Industry & Macro remain the hardest use cases across all systems, where even the best systems reach only 33% and 39%. We make the dataset and grading code publicly available.

cs.AI↗

arXiv2026

OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction

Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks. While most existing benchmarks assume simple, perfectly documented tools, real-world tools (e.g., general "search" APIs) are often opaque, lacking clear best practices or failure modes. Can LLM agents improve their performance in environments with opaque tools by interacting and subsequently improving documentation? To study this, we create OpaqueToolsBench, a benchmark consisting of three distinct task-oriented environments: general function calling, interactive chess playing, and long-trajectory agentic search. Each environment provides underspecified tools that models must learn to use effectively to complete the task. Results on OpaqueToolsBench suggest existing methods for automatically documenting tools are expensive and unreliable when tools are opaque. To address this, we propose a simple framework, ToolObserver, that iteratively refines tool documentation by observing execution feedback from tool-calling trajectories. Our approach outperforms existing methods on OpaqueToolsBench across datasets, even in relatively hard settings. Furthermore, for test-time tool exploration settings, our method is also efficient, consuming 3.5-7.5x fewer total tokens than the best baseline.

cs.CL↗

arXiv2025

Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search

Long-horizon agentic search requires iteratively exploring the web over long trajectories and synthesizing information across many sources, enabling powerful applications like deep research systems. In this work, we show that popular agentic search frameworks struggle to scale to long trajectories primarily due to context limitations--they accumulate long, noisy content, hit context window and tool budgets, or stop early. We therefore introduce SLIM (Simple Lightweight Information Management), a simple framework that separates retrieval into distinct search and browse tools, and periodically summarizes the trajectory, keeping context concise while enabling longer, more focused searches. Across a wide range of long-horizon tasks, SLIM achieves comparable performance at substantially lower cost and far fewer tool calls than strong open-source frameworks with both proprietary and open-weight models, including RL-trained models for deep research. Specifically, with o3 as the base model, SLIM achieves 56% on BrowseComp and 33% on HLE, outperforming all open-source frameworks by 8 and 6 absolute points, respectively, while incurring 4-6x fewer tool calls. With GLM-4.7 Flash, SLIM achieves 10 points improvement over the next best open-source framework, Search-o1, on BrowseComp using a third of the cost. To systematically understand failure modes in long-horizon agentic search, we develop an automated fine-grained trajectory analysis pipeline and error taxonomy, and find that SLIM exhibits significantly fewer hallucinations than prior systems. We hope our analysis framework and simple tool design inform future long-horizon agents.

cs.CL↗

arXiv2024

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be prompted like an LM. To train Promptriever, we curate and release a new instance-level instruction training set from MS MARCO, spanning nearly 500k instances. Promptriever not only achieves strong performance on standard retrieval tasks, but also follows instructions. We observe: (1) large gains (reaching SoTA) on following detailed relevance instructions (+14.3 p-MRR / +3.1 nDCG on FollowIR), (2) significantly increased robustness to lexical choices/phrasing in the query+instruction (+12.9 Robustness@10 on InstructIR), and (3) the ability to perform hyperparameter search via prompting to reliably improve retrieval performance (+1.4 average increase on BEIR). Promptriever demonstrates that retrieval models can be controlled with prompts on a per-query basis, setting the stage for future work aligning LM prompting techniques with information retrieval.

cs.IR↗

arXiv2024

Evaluating Human-Language Model Interaction

Many real-world applications of language models (LMs), such as writing assistance and code autocomplete, involve human-LM interaction. However, most benchmarks are non-interactive in that a model produces output without human involvement. To evaluate human-LM interaction, we develop a new framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems and dimensions to consider when designing evaluation metrics. Compared to standard, non-interactive evaluation, HALIE captures (i) the interactive process, not only the final output; (ii) the first-person subjective experience, not just a third-party assessment; and (iii) notions of preference beyond quality (e.g., enjoyment and ownership). We then design five tasks to cover different forms of interaction: social dialogue, question answering, crossword puzzles, summarization, and metaphor generation. With four state-of-the-art LMs (three variants of OpenAI's GPT-3 and AI21 Labs' Jurassic-1), we find that better non-interactive performance does not always translate to better human-LM interaction. In particular, we highlight three cases where the results from non-interactive and interactive metrics diverge and underscore the importance of human-LM interaction for LM evaluation.

cs.CL↗

arXiv2023

Lost in the Middle: How Language Models Use Long Contexts

While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of language models on two tasks that require identifying relevant information in their input contexts: multi-document question answering and key-value retrieval. We find that performance can degrade significantly when changing the position of relevant information, indicating that current language models do not robustly make use of information in long input contexts. In particular, we observe that performance is often highest when relevant information occurs at the beginning or end of the input context, and significantly degrades when models must access relevant information in the middle of long contexts, even for explicitly long-context models. Our analysis provides a better understanding of how language models use their input context and provides new evaluation protocols for future long-context language models.

cs.CL↗

arXiv2023

Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent

We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way. By integrating controlled neural generation with scaffolded, hand-written dialogue, we let both the user and bot take turns driving the conversation, producing an engaging and socially fluent experience. Deployed in the fourth iteration of the Alexa Prize Socialbot Grand Challenge, Chirpy Cardinal handled thousands of conversations per day, placing second out of nine bots with an average user rating of 3.58/5.

cs.CL↗

arXiv2022

You Only Need One Model for Open-domain Question Answering

Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model. Despite performing related tasks, the models have separate parameters and are weakly-coupled during training. We propose casting the retriever and the reranker as internal passage-wise attention mechanisms applied sequentially within the transformer architecture and feeding computed representations to the reader, with the hidden representations progressively refined at each stage. This allows us to use a single question answering model trained end-to-end, which is a more efficient use of model capacity and also leads to better gradient flow. We present a pre-training method to effectively train this architecture and evaluate our model on the Natural Questions and TriviaQA open datasets. For a fixed parameter budget, our model outperforms the previous state-of-the-art model by 1.0 and 0.7 exact match scores.

cs.CL↗

arXiv2022

When can I Speak? Predicting initiation points for spoken dialogue agents

Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow. Humans typically respond within 200ms and successfully predicting initiation points in advance would allow spoken dialogue agents to do the same. In this work, we predict the lead-time to initiation using prosodic features from a pre-trained speech representation model (wav2vec 1.0) operating on user audio and word features from a pre-trained language model (GPT-2) operating on incremental transcriptions. To evaluate errors, we propose two metrics w.r.t. predicted and true lead times. We train and evaluate the models on the Switchboard Corpus and find that our method outperforms features from prior work on both metrics and vastly outperforms the common approach of waiting for 700ms of silence.

cs.CL↗

arXiv2021

Hindsight: Posterior-guided training of retrievers for improved open-ended generation

Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e.g., Wikipedia) which are then provided as additional context to the generator. For open-ended generation tasks (like generating informative utterances in conversations) many varied passages may be equally relevant and we find that existing methods that jointly train the retriever and generator underperform: the retriever may not find relevant passages even amongst the top-10 and hence the generator may not learn a preference to ground its generated output in them. We propose using an additional guide retriever that is allowed to use the target output and "in hindsight" retrieve relevant passages during training. We model the guide retriever after the posterior distribution Q of passages given the input and the target output and train it jointly with the standard retriever and the generator by maximizing the evidence lower bound (ELBo) in expectation over Q. For informative conversations from the Wizard of Wikipedia dataset, with posterior-guided training, the retriever finds passages with higher relevance in the top-10 (23% relative improvement), the generator's responses are more grounded in the retrieved passage (19% relative improvement) and the end-to-end system produces better overall output (6.4% relative improvement).

cs.CL↗

arXiv2021

Human-like informative conversations: Better acknowledgements using conditional mutual information

This work aims to build a dialogue agent that can weave new factual content into conversations as naturally as humans. We draw insights from linguistic principles of conversational analysis and annotate human-human conversations from the Switchboard Dialog Act Corpus to examine humans strategies for acknowledgement, transition, detail selection and presentation. When current chatbots (explicitly provided with new factual content) introduce facts into a conversation, their generated responses do not acknowledge the prior turns. This is because models trained with two contexts - new factual content and conversational history - generate responses that are non-specific w.r.t. one of the contexts, typically the conversational history. We show that specificity w.r.t. conversational history is better captured by Pointwise Conditional Mutual Information ($\text{pcmi}_h$) than by the established use of Pointwise Mutual Information ($\text{pmi}$). Our proposed method, Fused-PCMI, trades off $\text{pmi}$ for $\text{pcmi}_h$ and is preferred by humans for overall quality over the Max-PMI baseline 60% of the time. Human evaluators also judge responses with higher $\text{pcmi}_h$ better at acknowledgement 74% of the time. The results demonstrate that systems mimicking human conversational traits (in this case acknowledgement) improve overall quality and more broadly illustrate the utility of linguistic principles in improving dialogue agents.

cs.CL↗

arXiv2020

Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations

We present Chirpy Cardinal, an open-domain dialogue agent, as a research platform for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging - such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms - prioritizing their interests, feelings and autonomy. As a result, our socialbot provides a responsive, personalized user experience, capable of talking knowledgeably about a wide variety of topics, as well as chatting empathetically about ordinary life. Neural generation plays a key role in achieving these goals, providing the backbone for our conversational and emotional tone. At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3.6/5.0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.

cs.CL↗

arXiv2018

Improving Website Hyperlink Structure Using Server Logs

Good websites should be easy to navigate via hyperlinks, yet maintaining a high-quality link structure is difficult. Identifying pairs of pages that should be linked may be hard for human editors, especially if the site is large and changes frequently. Further, given a set of useful link candidates, the task of incorporating them into the site can be expensive, since it typically involves humans editing pages. In the light of these challenges, it is desirable to develop data-driven methods for automating the link placement task. Here we develop an approach for automatically finding useful hyperlinks to add to a website. We show that passively collected server logs, beyond telling us which existing links are useful, also contain implicit signals indicating which nonexistent links would be useful if they were to be introduced. We leverage these signals to model the future usefulness of yet nonexistent links. Based on our model, we define the problem of link placement under budget constraints and propose an efficient algorithm for solving it. We demonstrate the effectiveness of our approach by evaluating it on Wikipedia, a large website for which we have access to both server logs (used for finding useful new links) and the complete revision history (containing a ground truth of new links). As our method is based exclusively on standard server logs, it may also be applied to any other website, as we show with the example of the biomedical research site Simtk.

cs.SI↗

arXiv2016

Motifs in Temporal Networks

Networks are a fundamental tool for modeling complex systems in a variety of domains including social and communication networks as well as biology and neuroscience. Small subgraph patterns in networks, called network motifs, are crucial to understanding the structure and function of these systems. However, the role of network motifs in temporal networks, which contain many timestamped links between the nodes, is not yet well understood. Here we develop a notion of a temporal network motif as an elementary unit of temporal networks and provide a general methodology for counting such motifs. We define temporal network motifs as induced subgraphs on sequences of temporal edges, design fast algorithms for counting temporal motifs, and prove their runtime complexity. Our fast algorithms achieve up to 56.5x speedup compared to a baseline method. Furthermore, we use our algorithms to count temporal motifs in a variety of networks. Results show that networks from different domains have significantly different motif counts, whereas networks from the same domain tend to have similar motif counts. We also find that different motifs occur at different time scales, which provides further insights into structure and function of temporal networks.

cs.SI↗

arXiv2015

Mining Missing Hyperlinks from Human Navigation Traces: A Case Study of Wikipedia

Hyperlinks are an essential feature of the World Wide Web. They are especially important for online encyclopedias such as Wikipedia: an article can often only be understood in the context of related articles, and hyperlinks make it easy to explore this context. But important links are often missing, and several methods have been proposed to alleviate this problem by learning a linking model based on the structure of the existing links. Here we propose a novel approach to identifying missing links in Wikipedia. We build on the fact that the ultimate purpose of Wikipedia links is to aid navigation. Rather than merely suggesting new links that are in tune with the structure of existing links, our method finds missing links that would immediately enhance Wikipedia's navigability. We leverage data sets of navigation paths collected through a Wikipedia-based human-computation game in which users must find a short path from a start to a target article by only clicking links encountered along the way. We harness human navigational traces to identify a set of candidates for missing links and then rank these candidates. Experiments show that our procedure identifies missing links of high quality.

cs.SI↗